Show of Hands:Votes: Party classification:: Votes_Q_02_cnk
bdanalytics
Date: (Sun) May 29, 2016
Introduction:
Data: Source: Training: “https://inclass.kaggle.com/c/can-we-predict-voting-outcomes/download/train2016.csv”
New: “https://inclass.kaggle.com/c/can-we-predict-voting-outcomes/download/test2016.csv”
Time period:
Synopsis:
Based on analysis utilizing <> techniques,
Summary of key steps & error improvement stats:
Prediction Accuracy Enhancement Options:
- transform.data chunk:
- derive features from multiple features
- manage.missing.data chunk:
- Not fill missing vars
- Fill missing numerics with a different algorithm
- Fill missing chars with data based on clusters
[](.png)
Potential next steps include:
- Organization:
- Categorize by chunk
- Priority criteria:
- Ease of change
- Impacts report
- Cleans innards
- Bug report
- all chunks:
- at chunk-end rm(!glb_)
- manage.missing.data chunk:
- cleaner way to manage re-splitting of training vs. new entity
- extract.features chunk:
- Add n-grams for glbFeatsText
- “RTextTools”, “tau”, “RWeka”, and “textcat” packages
- Add n-grams for glbFeatsText
- fit.models chunk:
- Classification: Plot AUC Curves for all models & highlight glbMdlSel
- Prediction accuracy scatter graph:
- Add tiles (raw vs. PCA)
- Use shiny for drop-down of “important” features
Use plot.ly for interactive plots ?
- Change .fit suffix of model metrics to .mdl if it’s data independent (e.g. AIC, Adj.R.Squared - is it truly data independent ?, etc.)
- create a custom model for rpart that has minbucket as a tuning parameter
varImp for randomForest crashes in caret version:6.0.41 -> submit bug report
- Probability handling for multinomials vs. desired binomial outcome
- ROCR currently supports only evaluation of binary classification tasks (version 1.0.7)
extensions toward multiclass classification are scheduled for the next release
- fit.all.training chunk:
- myplot_prediction_classification: displays ‘x’ instead of ‘+’ when there are no prediction errors
- Compare glb_sel_mdl vs. glb_fin_mdl:
- varImp
- Prediction differences (shd be minimal ?)
- Move glb_analytics_diag_plots to mydsutils.R: (+) Easier to debug (-) Too many glb vars used
- Add print(ggplot.petrinet(glb_analytics_pn) + coord_flip()) at the end of every major chunk
- Parameterize glb_analytics_pn
- Move glb_impute_missing_data to mydsutils.R: (-) Too many glb vars used; glb_<>_df reassigned
- Do non-glm methods handle interaction terms ?
- f-score computation for classifiers should be summation across outcomes (not just the desired one ?)
- Add accuracy computation to glb_dmy_mdl in predict.data.new chunk
- Why does splitting fit.data.training.all chunk into separate chunks add an overhead of ~30 secs ? It’s not rbind b/c other chunks have lower elapsed time. Is it the number of plots ?
- Incorporate code chunks in print_sessionInfo
- Test against
- projects in github.com/bdanalytics
- lectures in jhu-datascience track
Analysis:
rm(list = ls())
set.seed(12345)
options(stringsAsFactors = FALSE)
source("~/Dropbox/datascience/R/mycaret.R")
source("~/Dropbox/datascience/R/mydsutils.R")## Loading required package: caret## Loading required package: lattice## Loading required package: ggplot2source("~/Dropbox/datascience/R/mypetrinet.R")
source("~/Dropbox/datascience/R/myplclust.R")
source("~/Dropbox/datascience/R/myplot.R")
source("~/Dropbox/datascience/R/myscript.R")
source("~/Dropbox/datascience/R/mytm.R")
# Gather all package requirements here
suppressPackageStartupMessages(require(doMC))
glbCores <- 6 # of cores on machine - 2
registerDoMC(glbCores)
suppressPackageStartupMessages(require(caret))
require(plyr)## Loading required package: plyrrequire(dplyr)## Loading required package: dplyr##
## Attaching package: 'dplyr'## The following objects are masked from 'package:plyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionrequire(knitr)## Loading required package: knitrrequire(stringr)## Loading required package: stringr#source("dbgcaret.R")
#packageVersion("snow")
#require(sos); findFn("cosine", maxPages=2, sortby="MaxScore")
# Analysis control global variables
# Inputs
# url/name = "<PathPointer>"; if url specifies a zip file, name = "<filename>";
# or named collection of <PathPointer>s
# sep = choose from c(NULL, "\t")
glbObsTrnFile <- list(url = "https://inclass.kaggle.com/c/can-we-predict-voting-outcomes/download/train2016.csv"
# or list(url = c(NULL, <.inp1> = "<path1>", <.inp2> = "<path2>"))
#, splitSpecs = list(method = "copy" # default when glbObsNewFile is NULL
# select from c("copy", NULL ???, "condition", "sample", )
# ,nRatio = 0.3 # > 0 && < 1 if method == "sample"
# ,seed = 123 # any integer or glbObsTrnPartitionSeed if method == "sample"
# ,condition = # or 'is.na(<var>)'; '<var> <condition_operator> <value>'
# )
)
glbObsNewFile <- list(url = "https://inclass.kaggle.com/c/can-we-predict-voting-outcomes/download/test2016.csv")
glbObsDropCondition <- NULL # : default
# enclose in single-quotes b/c condition might include double qoutes
# use | & ; NOT || &&
# '<condition>'
# 'grepl("^First Draft Video:", glbObsAll$Headline)'
# 'is.na(glbObsAll[, glb_rsp_var_raw])'
# '(is.na(glbObsAll[, glb_rsp_var_raw]) & grepl("Train", glbObsAll[, glbFeatsId]))'
# 'is.na(strptime(glbObsAll[, "Date"], glbFeatsDateTime[["Date"]]["format"], tz = glbFeatsDateTime[["Date"]]["timezone"]))'
#nrow(do.call("subset",list(glbObsAll, parse(text=paste0("!(", glbObsDropCondition, ")")))))
glb_obs_repartition_train_condition <- NULL # : default
# "<condition>"
glb_max_fitobs <- NULL # or any integer
glbObsTrnPartitionSeed <- 123 # or any integer
glb_is_regression <- FALSE; glb_is_classification <- !glb_is_regression;
glb_is_binomial <- TRUE # or TRUE or FALSE
glb_rsp_var_raw <- "Party"
# for classification, the response variable has to be a factor
glb_rsp_var <- "Party.fctr"
# if the response factor is based on numbers/logicals e.g (0/1 OR TRUE/FALSE vs. "A"/"B"),
# or contains spaces (e.g. "Not in Labor Force")
# caret predict(..., type="prob") crashes
glb_map_rsp_raw_to_var <- #NULL
function(raw) {
# return(raw ^ 0.5)
# return(log(raw))
# return(log(1 + raw))
# return(log10(raw))
# return(exp(-raw / 2))
ret_vals <- rep_len(NA, length(raw)); ret_vals[!is.na(raw)] <- ifelse(raw[!is.na(raw)] == "Republican", "R", "D"); return(relevel(as.factor(ret_vals), ref = "R"))
# as.factor(paste0("B", raw))
# as.factor(gsub(" ", "\\.", raw))
}
#if glb_rsp_var_raw is numeric:
#print(summary(glbObsAll[, glb_rsp_var_raw]))
#glb_map_rsp_raw_to_var(tst <- c(NA, as.numeric(summary(glbObsAll[, glb_rsp_var_raw]))))
#if glb_rsp_var_raw is character:
#print(table(glbObsAll[, glb_rsp_var_raw], useNA = "ifany"))
# print(table(glb_map_rsp_raw_to_var(tst <- glbObsAll[, glb_rsp_var_raw]), useNA = "ifany"))
glb_map_rsp_var_to_raw <- #NULL
function(var) {
# return(var ^ 2.0)
# return(exp(var))
# return(10 ^ var)
# return(-log(var) * 2)
# as.numeric(var)
# levels(var)[as.numeric(var)]
sapply(levels(var)[as.numeric(var)], function(elm)
if (is.na(elm)) return(elm) else
if (elm == 'R') return("Republican") else
if (elm == 'D') return("Democrat") else
stop("glb_map_rsp_var_to_raw: unexpected value: ", elm)
)
# gsub("\\.", " ", levels(var)[as.numeric(var)])
# c("<=50K", " >50K")[as.numeric(var)]
# c(FALSE, TRUE)[as.numeric(var)]
}
# print(table(glb_map_rsp_var_to_raw(glb_map_rsp_raw_to_var(tst)), useNA = "ifany"))
if ((glb_rsp_var != glb_rsp_var_raw) && is.null(glb_map_rsp_raw_to_var))
stop("glb_map_rsp_raw_to_var function expected")
# List info gathered for various columns
# <col_name>: <description>; <notes>
# USER_ID - an anonymous id unique to a given user
# YOB - the year of birth of the user
# Gender - the gender of the user, either Male or Female
# Income - the household income of the user. Either not provided, or one of "under $25,000", "$25,001 - $50,000", "$50,000 - $74,999", "$75,000 - $100,000", "$100,001 - $150,000", or "over $150,000".
# HouseholdStatus - the household status of the user. Either not provided, or one of "Domestic Partners (no kids)", "Domestic Partners (w/kids)", "Married (no kids)", "Married (w/kids)", "Single (no kids)", or "Single (w/kids)".
# EducationalLevel - the education level of the user. Either not provided, or one of "Current K-12", "High School Diploma", "Current Undergraduate", "Associate's Degree", "Bachelor's Degree", "Master's Degree", or "Doctoral Degree".
# Party - the political party for whom the user intends to vote for. Either "Democrat" or "Republican
# Q124742, Q124122, . . . , Q96024 - 101 different questions that the users were asked on Show of Hands. If the user didn't answer the question, there is a blank. For information about the question text and possible answers, see the file Questions.pdf.
# currently does not handle more than 1 column; consider concatenating multiple columns
# If glbFeatsId == NULL, ".rownames <- as.numeric(row.names())" is the default
glbFeatsId <- "USER_ID" # choose from c(NULL : default, "<id_feat>")
# glbFeatsCategory <- "Hhold.fctr" # choose from c(NULL : default, "<category_feat>")
glbFeatsCategory <- "Q109244.fctr" # choose from c(NULL : default, "<category_feat>") -> OOB performed worse than "Hhold.fctr"
# User-specified exclusions
glbFeatsExclude <- c(NULL
# Feats that shd be excluded due to known causation by prediction variable
# , "<feat1", "<feat2>"
# Feats that are factors with unique values (as % of nObs) > 49 (empirically derived)
# Feats that are linear combinations (alias in glm)
# Feature-engineering phase -> start by excluding all features except id & category &
# work each one in
, "USER_ID", "YOB", "Gender", "Income", "HouseholdStatus", "EducationLevel"
,"Q124742","Q124122"
,"Q123621","Q123464"
,"Q122771","Q122770","Q122769","Q122120"
,"Q121700","Q121699","Q121011"
,"Q120978","Q120650","Q120472","Q120379","Q120194","Q120014","Q120012"
,"Q119851","Q119650","Q119334"
,"Q118892","Q118237","Q118233","Q118232","Q118117"
,"Q117193","Q117186"
,"Q116797","Q116881","Q116953","Q116601","Q116441","Q116448","Q116197"
,"Q115602","Q115777","Q115610","Q115611","Q115899","Q115390","Q115195"
,"Q114961","Q114748","Q114517","Q114386","Q114152"
,"Q113992","Q113583","Q113584","Q113181"
,"Q112478","Q112512","Q112270"
,"Q111848","Q111580","Q111220"
,"Q110740"
,"Q109367","Q109244"
,"Q108950","Q108855","Q108617","Q108856","Q108754","Q108342","Q108343"
,"Q107869","Q107491"
,"Q106993","Q106997","Q106272","Q106388","Q106389","Q106042"
,"Q105840","Q105655"
,"Q104996"
,"Q103293"
,"Q102906","Q102674","Q102687","Q102289","Q102089"
,"Q101162","Q101163","Q101596"
,"Q100689","Q100680","Q100562","Q100010"
,"Q99982"
,"Q99716"
,"Q99581"
,"Q99480"
,"Q98869"
,"Q98578"
,"Q98197"
,"Q98059","Q98078"
,"Q96024" # Done
,".pos")
if (glb_rsp_var_raw != glb_rsp_var)
glbFeatsExclude <- union(glbFeatsExclude, glb_rsp_var_raw)
glbFeatsInteractionOnly <- list()
#glbFeatsInteractionOnly[["<child_feat>"]] <- "<parent_feat>"
glbFeatsDrop <- c(NULL
# , "<feat1>", "<feat2>"
)
glb_map_vars <- NULL # or c("<var1>", "<var2>")
glb_map_urls <- list();
# glb_map_urls[["<var1>"]] <- "<var1.url>"
# Derived features; Use this mechanism to cleanse data ??? Cons: Data duplication ???
glbFeatsDerive <- list();
# glbFeatsDerive[["<feat.my.sfx>"]] <- list(
# mapfn = function(<arg1>, <arg2>) { return(function(<arg1>, <arg2>)) }
# , args = c("<arg1>", "<arg2>"))
#myprint_df(data.frame(ImageId = mapfn(glbObsAll$.src, glbObsAll$.pos)))
#data.frame(ImageId = mapfn(glbObsAll$.src, glbObsAll$.pos))[7045:7055, ]
# character
# mapfn = function(Education) { raw <- Education; raw[is.na(raw)] <- "NA.my"; return(as.factor(raw)) }
# mapfn = function(Week) { return(substr(Week, 1, 10)) }
# mapfn = function(Name) { return(sapply(Name, function(thsName)
# str_sub(unlist(str_split(thsName, ","))[1], 1, 1))) }
# mapfn = function(descriptor) { return(plyr::revalue(descriptor, c(
# "ABANDONED BUILDING" = "OTHER",
# "**" = "**"
# ))) }
# mapfn = function(description) { mod_raw <- description;
# This is here because it does not work if it's in txt_map_filename
# mod_raw <- gsub(paste0(c("\n", "\211", "\235", "\317", "\333"), collapse = "|"), " ", mod_raw)
# Don't parse for "." because of ".com"; use customized gsub for that text
# mod_raw <- gsub("(\\w)(!|\\*|,|-|/)(\\w)", "\\1\\2 \\3", mod_raw);
# Some state acrnoyms need context for separation e.g.
# LA/L.A. could either be "Louisiana" or "LosAngeles"
# modRaw <- gsub("\\bL\\.A\\.( |,|')", "LosAngeles\\1", modRaw);
# OK/O.K. could either be "Oklahoma" or "Okay"
# modRaw <- gsub("\\bACA OK\\b", "ACA OKay", modRaw);
# modRaw <- gsub("\\bNow O\\.K\\.\\b", "Now OKay", modRaw);
# PR/P.R. could either be "PuertoRico" or "Public Relations"
# modRaw <- gsub("\\bP\\.R\\. Campaign", "PublicRelations Campaign", modRaw);
# VA/V.A. could either be "Virginia" or "VeteransAdministration"
# modRaw <- gsub("\\bthe V\\.A\\.\\:", "the VeteranAffairs:", modRaw);
#
# Custom mods
# return(mod_raw) }
# numeric
# Create feature based on record position/id in data
glbFeatsDerive[[".pos"]] <- list(
mapfn = function(raw1) { return(1:length(raw1)) }
, args = c(".rnorm"))
# glbFeatsDerive[[".pos.y"]] <- list(
# mapfn = function(raw1) { return(1:length(raw1)) }
# , args = c(".rnorm"))
# Add logs of numerics that are not distributed normally
# Derive & keep multiple transformations of the same feature, if normality is hard to achieve with just one transformation
# Right skew: logp1; sqrt; ^ 1/3; logp1(logp1); log10; exp(-<feat>/constant)
# glbFeatsDerive[["WordCount.log1p"]] <- list(
# mapfn = function(WordCount) { return(log1p(WordCount)) }
# , args = c("WordCount"))
# glbFeatsDerive[["WordCount.root2"]] <- list(
# mapfn = function(WordCount) { return(WordCount ^ (1/2)) }
# , args = c("WordCount"))
# glbFeatsDerive[["WordCount.nexp"]] <- list(
# mapfn = function(WordCount) { return(exp(-WordCount)) }
# , args = c("WordCount"))
#print(summary(glbObsAll$WordCount))
#print(summary(mapfn(glbObsAll$WordCount)))
# If imputation shd be skipped for this feature
# glbFeatsDerive[["District.fctr"]] <- list(
# mapfn = function(District) {
# raw <- District;
# ret_vals <- rep_len("NA", length(raw));
# ret_vals[!is.na(raw)] <- sapply(raw[!is.na(raw)], function(elm)
# ifelse(elm < 10, "1-9",
# ifelse(elm < 20, "10-19", "20+")));
# return(relevel(as.factor(ret_vals), ref = "NA"))
# }
# , args = c("District"))
# YOB options:
# 1. Missing data:
# 1.1 0 -> Does not improve baseline
# 1.2 Cut factors & "NA" is a level
# 2. Data corrections: < 1928 & > 2000
# 3. Scale YOB
# 4. Add Age
glbFeatsDerive[["YOB.Age.fctr"]] <- list(
mapfn = function(raw1) {
raw <- 2016 - raw1
# raw[!is.na(raw) & raw >= 2010] <- NA
raw[!is.na(raw) & (raw <= 15)] <- NA
raw[!is.na(raw) & (raw >= 90)] <- NA
retVal <- rep_len("NA", length(raw))
# breaks = c(1879, seq(1949, 1989, 10), 2049)
# cutVal <- cut(raw[!is.na(raw)], breaks = breaks,
# labels = as.character(breaks + 1)[1:(length(breaks) - 1)])
cutVal <- cut(raw[!is.na(raw)], breaks = c(15, 20, 25, 30, 35, 40, 50, 65, 90))
retVal[!is.na(raw)] <- levels(cutVal)[cutVal]
return(factor(retVal, levels = c("NA"
,"(15,20]","(20,25]","(25,30]","(30,35]","(35,40]","(40,50]","(50,65]","(65,90]"),
ordered = TRUE))
}
, args = c("YOB"))
glbFeatsDerive[["Gender.fctr"]] <- list(
mapfn = function(raw1) {
raw <- raw1
raw[raw %in% ""] <- "N"
raw <- gsub("Male" , "M", raw, fixed = TRUE)
raw <- gsub("Female", "F", raw, fixed = TRUE)
return(relevel(as.factor(raw), ref = "N"))
}
, args = c("Gender"))
glbFeatsDerive[["Income.fctr"]] <- list(
mapfn = function(raw1) { raw <- raw1;
raw[raw %in% ""] <- "N"
raw <- gsub("under $25,000" , "<25K" , raw, fixed = TRUE)
raw <- gsub("$25,001 - $50,000" , "25-50K" , raw, fixed = TRUE)
raw <- gsub("$50,000 - $74,999" , "50-75K" , raw, fixed = TRUE)
raw <- gsub("$75,000 - $100,000" , "75-100K" , raw, fixed = TRUE)
raw <- gsub("$100,001 - $150,000", "100-150K", raw, fixed = TRUE)
raw <- gsub("over $150,000" , ">150K" , raw, fixed = TRUE)
return(factor(raw, levels = c("N","<25K","25-50K","50-75K","75-100K","100-150K",">150K"),
ordered = TRUE))
}
, args = c("Income"))
glbFeatsDerive[["Hhold.fctr"]] <- list(
mapfn = function(raw1) { raw <- raw1;
raw[raw %in% ""] <- "N"
raw <- gsub("Domestic Partners (no kids)", "PKn", raw, fixed = TRUE)
raw <- gsub("Domestic Partners (w/kids)" , "PKy", raw, fixed = TRUE)
raw <- gsub("Married (no kids)" , "MKn", raw, fixed = TRUE)
raw <- gsub("Married (w/kids)" , "MKy", raw, fixed = TRUE)
raw <- gsub("Single (no kids)" , "SKn", raw, fixed = TRUE)
raw <- gsub("Single (w/kids)" , "SKy", raw, fixed = TRUE)
return(relevel(as.factor(raw), ref = "N"))
}
, args = c("HouseholdStatus"))
glbFeatsDerive[["Edn.fctr"]] <- list(
mapfn = function(raw1) { raw <- raw1;
raw[raw %in% ""] <- "N"
raw <- gsub("Current K-12" , "K12", raw, fixed = TRUE)
raw <- gsub("High School Diploma" , "HSD", raw, fixed = TRUE)
raw <- gsub("Current Undergraduate", "CCg", raw, fixed = TRUE)
raw <- gsub("Associate's Degree" , "Ast", raw, fixed = TRUE)
raw <- gsub("Bachelor's Degree" , "Bcr", raw, fixed = TRUE)
raw <- gsub("Master's Degree" , "Msr", raw, fixed = TRUE)
raw <- gsub("Doctoral Degree" , "PhD", raw, fixed = TRUE)
return(factor(raw, levels = c("N","K12","HSD","CCg","Ast","Bcr","Msr","PhD"),
ordered = TRUE))
}
, args = c("EducationLevel"))
# for (qsn in c("Q124742","Q124122"))
# for (qsn in grep("Q12(.{4})(?!\\.fctr)", names(glbObsTrn), value = TRUE, perl = TRUE))
for (qsn in grep("Q", glbFeatsExclude, fixed = TRUE, value = TRUE))
glbFeatsDerive[[paste0(qsn, ".fctr")]] <- list(
mapfn = function(raw1) {
raw1[raw1 %in% ""] <- "NA"
rawVal <- unique(raw1)
if (length(setdiff(rawVal, (expVal <- c("NA", "No", "Ys")))) == 0) {
raw1 <- gsub("Yes", "Ys", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
} else
if (length(setdiff(rawVal, (expVal <- c("NA", "Me", "Circumstances")))) == 0) {
raw1 <- gsub("Circumstances", "Cs", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
} else
if (length(setdiff(rawVal, (expVal <- c("NA", "Grrr people", "Yay people!")))) == 0) {
raw1 <- gsub("Grrr people", "Gr", raw1, fixed = TRUE)
raw1 <- gsub("Yay people!", "Yy", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
} else
if (length(setdiff(rawVal, (expVal <- c("NA", "Idealist", "Pragmatist")))) == 0) {
raw1 <- gsub("Idealist" , "Id", raw1, fixed = TRUE)
raw1 <- gsub("Pragmatist", "Pr", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
} else
if (length(setdiff(rawVal, (expVal <- c("NA", "Private", "Public")))) == 0) {
raw1 <- gsub("Private", "Pt", raw1, fixed = TRUE)
raw1 <- gsub("Public" , "Pc", raw1, fixed = TRUE)
if (length(setdiff(rawVal, expVal)) > 0)
stop(qsn, " vals: ", paste0(rawVal, collapse = "|"),
" does not match expectation: ", paste0(expVal, collapse = "|"))
}
return(relevel(as.factor(raw1), ref = "NA"))
}
, args = c(qsn))
# If imputation of missing data is not working ...
# glbFeatsDerive[["FertilityRate.nonNA"]] <- list(
# mapfn = function(FertilityRate, Region) {
# RegionMdn <- tapply(FertilityRate, Region, FUN = median, na.rm = TRUE)
#
# retVal <- FertilityRate
# retVal[is.na(FertilityRate)] <- RegionMdn[Region[is.na(FertilityRate)]]
# return(retVal)
# }
# , args = c("FertilityRate", "Region"))
# mapfn = function(HOSPI.COST) { return(cut(HOSPI.COST, 5, breaks = c(0, 100000, 200000, 300000, 900000), labels = NULL)) }
# mapfn = function(Rasmussen) { return(ifelse(sign(Rasmussen) >= 0, 1, 0)) }
# mapfn = function(startprice) { return(startprice ^ (1/2)) }
# mapfn = function(startprice) { return(log(startprice)) }
# mapfn = function(startprice) { return(exp(-startprice / 20)) }
# mapfn = function(startprice) { return(scale(log(startprice))) }
# mapfn = function(startprice) { return(sign(sprice.predict.diff) * (abs(sprice.predict.diff) ^ (1/10))) }
# factor
# mapfn = function(PropR) { return(as.factor(ifelse(PropR >= 0.5, "Y", "N"))) }
# mapfn = function(productline, description) { as.factor(gsub(" ", "", productline)) }
# mapfn = function(purpose) { return(relevel(as.factor(purpose), ref="all_other")) }
# mapfn = function(raw) { tfr_raw <- as.character(cut(raw, 5));
# tfr_raw[is.na(tfr_raw)] <- "NA.my";
# return(as.factor(tfr_raw)) }
# mapfn = function(startprice.log10) { return(cut(startprice.log10, 3)) }
# mapfn = function(startprice.log10) { return(cut(sprice.predict.diff, c(-1000, -100, -10, -1, 0, 1, 10, 100, 1000))) }
# , args = c("<arg1>"))
# multiple args
# mapfn = function(id, date) { return(paste(as.character(id), as.character(date), sep = "#")) }
# mapfn = function(PTS, oppPTS) { return(PTS - oppPTS) }
# mapfn = function(startprice.log10.predict, startprice) {
# return(spdiff <- (10 ^ startprice.log10.predict) - startprice) }
# mapfn = function(productline, description) { as.factor(
# paste(gsub(" ", "", productline), as.numeric(nchar(description) > 0), sep = "*")) }
# mapfn = function(.src, .pos) {
# return(paste(.src, sprintf("%04d",
# ifelse(.src == "Train", .pos, .pos - 7049)
# ), sep = "#")) }
# # If glbObsAll is not sorted in the desired manner
# mapfn=function(Week) { return(coredata(lag(zoo(orderBy(~Week, glbObsAll)$ILI), -2, na.pad=TRUE))) }
# mapfn=function(ILI) { return(coredata(lag(zoo(ILI), -2, na.pad=TRUE))) }
# mapfn=function(ILI.2.lag) { return(log(ILI.2.lag)) }
# glbFeatsDerive[["<var1>"]] <- glbFeatsDerive[["<var2>"]]
# tst <- "descr.my"; args_lst <- NULL; for (arg in glbFeatsDerive[[tst]]$args) args_lst[[arg]] <- glbObsAll[, arg]; print(head(args_lst[[arg]])); print(head(drv_vals <- do.call(glbFeatsDerive[[tst]]$mapfn, args_lst)));
# print(which_ix <- which(args_lst[[arg]] == 0.75)); print(drv_vals[which_ix]);
glbFeatsDateTime <- list()
# Use OlsonNames() to enumerate supported time zones
# glbFeatsDateTime[["<DateTimeFeat>"]] <-
# c(format = "%Y-%m-%d %H:%M:%S" or "%m/%e/%y", timezone = "US/Eastern", impute.na = TRUE,
# last.ctg = FALSE, poly.ctg = FALSE)
glbFeatsPrice <- NULL # or c("<price_var>")
glbFeatsImage <- list() #list(<imageFeat> = list(patchSize = 10)) # if patchSize not specified, no patch computation
glbFeatsText <- list()
Sys.setlocale("LC_ALL", "C") # For english## [1] "C/C/C/C/C/en_US.UTF-8"#glbFeatsText[["<TextFeature>"]] <- list(NULL,
# ,names = myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL,
# <comma-separated-screened-names>
# ))))
# ,rareWords = myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL,
# <comma-separated-nonSCOWL-words>
# ))))
#)
# Text Processing Step: custom modifications not present in txt_munge -> use glbFeatsDerive
# Text Processing Step: universal modifications
glb_txt_munge_filenames_pfx <- "<projectId>_mytxt_"
# Text Processing Step: tolower
# Text Processing Step: myreplacePunctuation
# Text Processing Step: removeWords
glb_txt_stop_words <- list()
# Remember to use unstemmed words
if (length(glbFeatsText) > 0) {
require(tm)
require(stringr)
glb_txt_stop_words[["<txt_var>"]] <- sort(myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# Remove any words from stopwords
# , setdiff(myreplacePunctuation(stopwords("english")), c("<keep_wrd1>", <keep_wrd2>"))
# Remove salutations
,"mr","mrs","dr","Rev"
# Remove misc
#,"th" # Happy [[:digit::]]+th birthday
# Remove terms present in Trn only or New only; search for "Partition post-stem"
# ,<comma-separated-terms>
# cor.y.train == NA
# ,unlist(strsplit(paste(c(NULL
# ,"<comma-separated-terms>"
# ), collapse=",")
# freq == 1; keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
# chisq.pval high (e.g. == 1); keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
# nzv.freqRatio high (e.g. >= glbFeatsNzvFreqMax); keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
)))))
}
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^man", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
#glbObsAll[glb_post_stem_words_terms_mtrx_lst[[txtFeat]][, 4866] > 0, c(glb_rsp_var, txtFeat)]
# To identify terms with a specific freq
#paste0(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], freq == 1)$term), collapse = ",")
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], freq <= 2)$term), collapse = ",")
#subset(glb_post_stem_words_terms_df_lst[[txtFeat]], term %in% c("zinger"))
# To identify terms with a specific freq &
# are not stemmed together later OR is value of color.fctr (e.g. gold)
#paste0(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], (freq == 1) & !(term %in% c("blacked","blemish","blocked","blocks","buying","cables","careful","carefully","changed","changing","chargers","cleanly","cleared","connect","connects","connected","contains","cosmetics","default","defaulting","defective","definitely","describe","described","devices","displays","drop","drops","engravement","excellant","excellently","feels","fix","flawlessly","frame","framing","gentle","gold","guarantee","guarantees","handled","handling","having","install","iphone","iphones","keeped","keeps","known","lights","line","lining","liquid","liquidation","looking","lots","manuals","manufacture","minis","most","mostly","network","networks","noted","opening","operated","performance","performs","person","personalized","photograph","physically","placed","places","powering","pre","previously","products","protection","purchasing","returned","rotate","rotation","running","sales","second","seconds","shipped","shuts","sides","skin","skinned","sticker","storing","thats","theres","touching","unusable","update","updates","upgrade","weeks","wrapped","verified","verify") ))$term), collapse = ",")
#print(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (freq <= 2)))
#glbObsAll[which(terms_mtrx[, 229] > 0), glbFeatsText]
# To identify terms with cor.y == NA
#orderBy(~-freq+term, subset(glb_post_stop_words_terms_df_lst[[txtFeat]], is.na(cor.y)))
#paste(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], is.na(cor.y))[, "term"]), collapse=",")
#orderBy(~-freq+term, subset(glb_post_stem_words_terms_df_lst[[txtFeat]], is.na(cor.y)))
# To identify terms with low cor.y.abs
#head(orderBy(~cor.y.abs+freq+term, subset(glb_post_stem_words_terms_df_lst[[txtFeat]], !is.na(cor.y))), 5)
# To identify terms with high chisq.pval
#subset(glb_post_stem_words_terms_df_lst[[txtFeat]], chisq.pval > 0.99)
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (chisq.pval > 0.99) & (freq <= 10))$term), collapse=",")
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (chisq.pval > 0.9))$term), collapse=",")
#head(orderBy(~-chisq.pval+freq+term, glb_post_stem_words_terms_df_lst[[txtFeat]]), 5)
#glbObsAll[glb_post_stem_words_terms_mtrx_lst[[txtFeat]][, 68] > 0, glbFeatsText]
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^m", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
# To identify terms with high nzv.freqRatio
#summary(glb_post_stem_words_terms_df_lst[[txtFeat]]$nzv.freqRatio)
#paste0(sort(setdiff(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (nzv.freqRatio >= glbFeatsNzvFreqMax) & (freq < 10) & (chisq.pval >= 0.05))$term, c( "128gb","3g","4g","gold","ipad1","ipad3","ipad4","ipadair2","ipadmini2","manufactur","spacegray","sprint","tmobil","verizon","wifion"))), collapse=",")
# To identify obs with a txt term
#tail(orderBy(~-freq+term, glb_post_stop_words_terms_df_lst[[txtFeat]]), 20)
#mydspObs(list(descr.my.contains="non"), cols=c("color", "carrier", "cellular", "storage"))
#grep("ever", dimnames(terms_stop_mtrx)$Terms)
#which(terms_stop_mtrx[, grep("ipad", dimnames(terms_stop_mtrx)$Terms)] > 0)
#glbObsAll[which(terms_stop_mtrx[, grep("16", dimnames(terms_stop_mtrx)$Terms)[1]] > 0), c(glbFeatsCategory, "storage", txtFeat)]
# Text Processing Step: screen for names # Move to glbFeatsText specs section in order of text processing steps
# glbFeatsText[["<txtFeat>"]]$names <- myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# # Person names for names screening
# ,<comma-separated-list>
#
# # Company names
# ,<comma-separated-list>
#
# # Product names
# ,<comma-separated-list>
# ))))
# glbFeatsText[["<txtFeat>"]]$rareWords <- myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# # Words not in SCOWL db
# ,<comma-separated-list>
# ))))
# To identify char vectors post glbFeatsTextMap
#grep("six(.*)hour", glb_txt_chr_lst[[txtFeat]], ignore.case = TRUE, value = TRUE)
#grep("[S|s]ix(.*)[H|h]our", glb_txt_chr_lst[[txtFeat]], value = TRUE)
# To identify whether terms shd be synonyms
#orderBy(~term, glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^moder", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ])
# term_row_df <- glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^came$", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ]
#
# cor(glb_post_stop_words_terms_mtrx_lst[[txtFeat]][glbObsAll$.lcn == "Fit", term_row_df$pos], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
# To identify which stopped words are "close" to a txt term
#sort(glbFeatsCluster)
# Text Processing Step: stemDocument
# To identify stemmed txt terms
#glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^la$", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ]
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^con", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
#glbObsAll[which(terms_stem_mtrx[, grep("use", dimnames(terms_stem_mtrx)$Terms)[[1]]] > 0), c(glbFeatsId, "productline", txtFeat)]
#glbObsAll[which(TfIdf_stem_mtrx[, 191] > 0), c(glbFeatsId, glbFeatsCategory, txtFeat)]
#glbObsAll[which(glb_post_stop_words_terms_mtrx_lst[[txtFeat]][, 6165] > 0), c(glbFeatsId, glbFeatsCategory, txtFeat)]
#which(glbObsAll$UniqueID %in% c(11915, 11926, 12198))
# Text Processing Step: mycombineSynonyms
# To identify which terms are associated with not -> combine "could not" & "couldn't"
#findAssocs(glb_full_DTM_lst[[txtFeat]], "not", 0.05)
# To identify which synonyms should be combined
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^c", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
chk_comb_cor <- function(syn_lst) {
# cor(terms_stem_mtrx[glbObsAll$.src == "Train", grep("^(damag|dent|ding)$", dimnames(terms_stem_mtrx)[[2]])], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
print(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], term %in% syn_lst$syns))
print(subset(get_corpus_terms(tm_map(glbFeatsTextCorpus[[txtFeat]], mycombineSynonyms, list(syn_lst), lazy=FALSE)), term == syn_lst$word))
# cor(terms_stop_mtrx[glbObsAll$.src == "Train", grep("^(damage|dent|ding)$", dimnames(terms_stop_mtrx)[[2]])], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
# cor(rowSums(terms_stop_mtrx[glbObsAll$.src == "Train", grep("^(damage|dent|ding)$", dimnames(terms_stop_mtrx)[[2]])]), glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
}
#chk_comb_cor(syn_lst=list(word="cabl", syns=c("cabl", "cord")))
#chk_comb_cor(syn_lst=list(word="damag", syns=c("damag", "dent", "ding")))
#chk_comb_cor(syn_lst=list(word="dent", syns=c("dent", "ding")))
#chk_comb_cor(syn_lst=list(word="use", syns=c("use", "usag")))
glbFeatsTextSynonyms <- list()
# list parsed to collect glbFeatsText[[<txtFeat>]]$vldTerms
# glbFeatsTextSynonyms[["Hdln.my"]] <- list(NULL
# # people in places
# , list(word = "australia", syns = c("australia", "australian"))
# , list(word = "italy", syns = c("italy", "Italian"))
# , list(word = "newyork", syns = c("newyork", "newyorker"))
# , list(word = "Pakistan", syns = c("Pakistan", "Pakistani"))
# , list(word = "peru", syns = c("peru", "peruvian"))
# , list(word = "qatar", syns = c("qatar", "qatari"))
# , list(word = "scotland", syns = c("scotland", "scotish"))
# , list(word = "Shanghai", syns = c("Shanghai", "Shanzhai"))
# , list(word = "venezuela", syns = c("venezuela", "venezuelan"))
#
# # companies - needs to be data dependent
# # - e.g. ensure BNP in this experiment/feat always refers to BNPParibas
#
# # general synonyms
# , list(word = "Create", syns = c("Create","Creator"))
# , list(word = "cute", syns = c("cute","cutest"))
# , list(word = "Disappear", syns = c("Disappear","Fadeout"))
# , list(word = "teach", syns = c("teach", "taught"))
# , list(word = "theater", syns = c("theater", "theatre", "theatres"))
# , list(word = "understand", syns = c("understand", "understood"))
# , list(word = "weak", syns = c("weak", "weaken", "weaker", "weakest"))
# , list(word = "wealth", syns = c("wealth", "wealthi"))
#
# # custom synonyms (phrases)
#
# # custom synonyms (names)
# )
#glbFeatsTextSynonyms[["<txtFeat>"]] <- list(NULL
# , list(word="<stem1>", syns=c("<stem1>", "<stem1_2>"))
# )
for (txtFeat in names(glbFeatsTextSynonyms))
for (entryIx in 1:length(glbFeatsTextSynonyms[[txtFeat]])) {
glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$word <-
str_to_lower(glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$word)
glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$syns <-
str_to_lower(glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$syns)
}
glbFeatsTextSeed <- 181
# tm options include: check tm::weightSMART
glb_txt_terms_control <- list( # Gather model performance & run-time stats
# weighting = function(x) weightSMART(x, spec = "nnn")
# weighting = function(x) weightSMART(x, spec = "lnn")
# weighting = function(x) weightSMART(x, spec = "ann")
# weighting = function(x) weightSMART(x, spec = "bnn")
# weighting = function(x) weightSMART(x, spec = "Lnn")
#
weighting = function(x) weightSMART(x, spec = "ltn") # default
# weighting = function(x) weightSMART(x, spec = "lpn")
#
# weighting = function(x) weightSMART(x, spec = "ltc")
#
# weighting = weightBin
# weighting = weightTf
# weighting = weightTfIdf # : default
# termFreq selection criteria across obs: tm default: list(global=c(1, Inf))
, bounds = list(global = c(1, Inf))
# wordLengths selection criteria: tm default: c(3, Inf)
, wordLengths = c(1, Inf)
)
glb_txt_cor_var <- glb_rsp_var # : default # or c(<feat>)
# select one from c("union.top.val.cor", "top.cor", "top.val", default: "top.chisq", "sparse")
glbFeatsTextFilter <- "top.chisq"
glbFeatsTextTermsMax <- rep(10, length(glbFeatsText)) # :default
names(glbFeatsTextTermsMax) <- names(glbFeatsText)
# Text Processing Step: extractAssoc
glbFeatsTextAssocCor <- rep(1, length(glbFeatsText)) # :default
names(glbFeatsTextAssocCor) <- names(glbFeatsText)
# Remember to use stemmed terms
glb_important_terms <- list()
# Text Processing Step: extractPatterns (ngrams)
glbFeatsTextPatterns <- list()
#glbFeatsTextPatterns[[<txtFeat>>]] <- list()
#glbFeatsTextPatterns[[<txtFeat>>]] <- c(metropolitan.diary.colon = "Metropolitan Diary:")
# Have to set it even if it is not used
# Properties:
# numrows(glb_feats_df) << numrows(glbObsFit
# Select terms that appear in at least 0.2 * O(FP/FN(glbObsOOB)) ???
# numrows(glbObsOOB) = 1.1 * numrows(glbObsNew) ???
glb_sprs_thresholds <- NULL # or c(<txtFeat1> = 0.988, <txtFeat2> = 0.970, <txtFeat3> = 0.970)
glbFctrMaxUniqVals <- 20 # default: 20
glb_impute_na_data <- FALSE # or TRUE
glb_mice_complete.seed <- 144 # or any integer
glb_cluster <- FALSE # : default or TRUE
glb_cluster.seed <- 189 # or any integer
glb_cluster_entropy_var <- NULL # c(glb_rsp_var, as.factor(cut(glb_rsp_var, 3)), default: NULL)
glbFeatsTextClusterVarsExclude <- FALSE # default FALSE
glb_interaction_only_feats <- NULL # : default or c(<parent_feat> = "<child_feat>")
glbFeatsNzvFreqMax <- 19 # 19 : caret default
glbFeatsNzvUniqMin <- 10 # 10 : caret default
glbRFESizes <- list()
#glbRFESizes[["mdlFamily"]] <- c(4, 8, 16, 32, 64, 67, 68, 69) # Accuracy@69/70 = 0.8258
glbObsFitOutliers <- list()
# If outliers.n >= 10; consider concatenation of interaction vars
# glbObsFitOutliers[["<mdlFamily>"]] <- c(NULL
# is.na(.rstudent)
# max(.rstudent)
# is.na(.dffits)
# .hatvalues >= 0.99
# -38,167,642 < minmax(.rstudent) < 49,649,823
# , <comma-separated-<glbFeatsId>>
# )
glbObsTrnOutliers <- list()
glbObsTrnOutliers[["Final"]] <- union(glbObsFitOutliers[["All.X"]],
c(NULL
))
# influence.measures: car::outlier; rstudent; dffits; hatvalues; dfbeta; dfbetas
#mdlId <- "All.X##rcv#glm"; obs_df <- fitobs_df
#mdlId <- "RFE.X.glm"; obs_df <- fitobs_df
#mdlId <- "Final.glm"; obs_df <- trnobs_df
#mdlId <- "CSM2.X.glm"; obs_df <- fitobs_df
#print(outliers <- car::outlierTest(glb_models_lst[[mdlId]]$finalModel))
#mdlIdFamily <- paste0(head(unlist(str_split(mdlId, "\\.")), -1), collapse="."); obs_df <- dplyr::filter_(obs_df, interp(~(!(var %in% glbObsFitOutliers[[mdlIdFamily]])), var = as.name(glbFeatsId))); model_diags_df <- cbind(obs_df, data.frame(.rstudent=stats::rstudent(glb_models_lst[[mdlId]]$finalModel)), data.frame(.dffits=stats::dffits(glb_models_lst[[mdlId]]$finalModel)), data.frame(.hatvalues=stats::hatvalues(glb_models_lst[[mdlId]]$finalModel)));print(summary(model_diags_df[, c(".rstudent",".dffits",".hatvalues")])); table(cut(model_diags_df$.hatvalues, breaks=c(0.00, 0.98, 0.99, 1.00)))
#print(subset(model_diags_df, is.na(.rstudent))[, glbFeatsId])
#print(model_diags_df[which.max(model_diags_df$.rstudent), ])
#print(subset(model_diags_df, is.na(.dffits))[, glbFeatsId])
#print(model_diags_df[which.min(model_diags_df$.dffits), ])
#print(subset(model_diags_df, .hatvalues > 0.99)[, glbFeatsId])
#dffits_df <- merge(dffits_df, outliers_df, by="row.names", all.x=TRUE); row.names(dffits_df) <- dffits_df$Row.names; dffits_df <- subset(dffits_df, select=-Row.names)
#dffits_df <- merge(dffits_df, glbObsFit, by="row.names", all.x=TRUE); row.names(dffits_df) <- dffits_df$Row.names; dffits_df <- subset(dffits_df, select=-Row.names)
#subset(dffits_df, !is.na(.Bonf.p))
#mdlId <- "CSM.X.glm"; vars <- myextract_actual_feats(row.names(orderBy(reformulate(c("-", paste0(mdlId, ".imp"))), myget_feats_imp(glb_models_lst[[mdlId]]))));
#model_diags_df <- glb_get_predictions(model_diags_df, mdlId, glb_rsp_var)
#obs_ix <- row.names(model_diags_df) %in% names(outliers$rstudent)[1]
#obs_ix <- which(is.na(model_diags_df$.rstudent))
#obs_ix <- which(is.na(model_diags_df$.dffits))
#myplot_parcoord(obs_df=model_diags_df[, c(glbFeatsId, glbFeatsCategory, ".rstudent", ".dffits", ".hatvalues", glb_rsp_var, paste0(glb_rsp_var, mdlId), vars[1:min(20, length(vars))])], obs_ix=obs_ix, id_var=glbFeatsId, category_var=glbFeatsCategory)
#model_diags_df[row.names(model_diags_df) %in% names(outliers$rstudent)[c(1:2)], ]
#ctgry_diags_df <- model_diags_df[model_diags_df[, glbFeatsCategory] %in% c("Unknown#0"), ]
#myplot_parcoord(obs_df=ctgry_diags_df[, c(glbFeatsId, glbFeatsCategory, ".rstudent", ".dffits", ".hatvalues", glb_rsp_var, "startprice.log10.predict.RFE.X.glmnet", indepVar[1:20])], obs_ix=row.names(ctgry_diags_df) %in% names(outliers$rstudent)[1], id_var=glbFeatsId, category_var=glbFeatsCategory)
#table(glbObsFit[model_diags_df[, glbFeatsCategory] %in% c("iPad1#1"), "startprice.log10.cut.fctr"])
#glbObsFit[model_diags_df[, glbFeatsCategory] %in% c("iPad1#1"), c(glbFeatsId, "startprice")]
# No outliers & .dffits == NaN
#myplot_parcoord(obs_df=model_diags_df[, c(glbFeatsId, glbFeatsCategory, glb_rsp_var, "startprice.log10.predict.RFE.X.glmnet", indepVar[1:10])], obs_ix=seq(1:nrow(model_diags_df))[is.na(model_diags_df$.dffits)], id_var=glbFeatsId, category_var=glbFeatsCategory)
# Modify mdlId to (build & extract) "<FamilyId>#<Fit|Trn>#<caretMethod>#<preProc1.preProc2>#<samplingMethod>"
glb_models_lst <- list(); glb_models_df <- data.frame()
# Add xgboost algorithm
# Regression
if (glb_is_regression) {
glbMdlMethods <- c(NULL
# deterministic
#, "lm", # same as glm
, "glm", "bayesglm", "glmnet"
, "rpart"
# non-deterministic
, "gbm", "rf"
# Unknown
, "nnet" , "avNNet" # runs 25 models per cv sample for tunelength=5
, "svmLinear", "svmLinear2"
, "svmPoly" # runs 75 models per cv sample for tunelength=5
, "svmRadial"
, "earth"
, "bagEarth" # Takes a long time
,"xgbLinear","xgbTree"
)
} else
# Classification - Add ada (auto feature selection)
if (glb_is_binomial)
glbMdlMethods <- c(NULL
# deterministic
, "bagEarth" # Takes a long time
, "glm", "bayesglm", "glmnet"
, "nnet"
, "rpart"
# non-deterministic
, "gbm"
, "avNNet" # runs 25 models per cv sample for tunelength=5
, "rf"
# Unknown
, "lda", "lda2"
# svm models crash when predict is called -> internal to kernlab it should call predict without .outcome
, "svmLinear", "svmLinear2"
, "svmPoly" # runs 75 models per cv sample for tunelength=5
, "svmRadial"
, "earth"
,"xgbLinear","xgbTree"
) else
glbMdlMethods <- c(NULL
# deterministic
,"glmnet"
# non-deterministic
,"rf"
# Unknown
,"gbm","rpart","xgbLinear","xgbTree"
)
glbMdlFamilies <- list(); glb_mdl_feats_lst <- list()
# family: Choose from c("RFE.X", "CSM.X", "All.X", "Best.Interact")
# methods: Choose from c(NULL, <method>, glbMdlMethods)
#glbMdlFamilies[["RFE.X"]] <- c("glmnet", "glm") # non-NULL vector is mandatory
if (glb_is_classification && !glb_is_binomial)
# glm does not work for multinomial
glbMdlFamilies[["All.X"]] <- c("glmnet") else
glbMdlFamilies[["All.X"]] <- c("glmnet", "glm")
#glbMdlFamilies[["Best.Interact"]] <- "glmnet" # non-NULL vector is mandatory
# Check if interaction features make RFE better
# glbMdlFamilies[["CSM.X"]] <- setdiff(glbMdlMethods, c("lda", "lda2")) # crashing due to category:.clusterid ??? #c("glmnet", "glm") # non-NULL list is mandatory
# glb_mdl_feats_lst[["CSM.X"]] <- c(NULL
# , <comma-separated-features-vector>
# )
# dAFeats.CSM.X %<d-% c(NULL
# # Interaction feats up to varImp(RFE.X.glmnet) >= 50
# , <comma-separated-features-vector>
# , setdiff(myextract_actual_feats(predictors(rfe_fit_results)), c(NULL
# , <comma-separated-features-vector>
# ))
# )
# glb_mdl_feats_lst[["CSM.X"]] <- "%<d-% dAFeats.CSM.X"
glbMdlFamilies[["Final"]] <- c(NULL) # NULL vector acceptable # c("glmnet", "glm")
glbMdlAllowParallel <- list()
#glbMdlAllowParallel[["Final##rcv#glmnet"]] <- FALSE
glbMdlAllowParallel[["All.X##rcv#glm"]] <- FALSE
# Check if tuning parameters make fit better; make it mdlFamily customizable ?
glbMdlTuneParams <- data.frame()
# When glmnet crashes at model$grid with error: ???
glmnetTuneParams <- rbind(data.frame()
,data.frame(parameter = "alpha", vals = "0.100 0.325 0.550 0.775 1.000")
,data.frame(parameter = "lambda", vals = "9.342e-02")
)
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams,
# cbind(data.frame(mdlId = "<mdlId>"),
# glmnetTuneParams))
#avNNet
# size=[1] 3 5 7 9; decay=[0] 1e-04 0.001 0.01 0.1; bag=[FALSE]; RMSE=1.3300906
#bagEarth
# degree=1 [2] 3; nprune=64 128 256 512 [1024]; RMSE=0.6486663 (up)
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "bagEarth", parameter = "nprune", vals = "256")
# ,data.frame(method = "bagEarth", parameter = "degree", vals = "2")
# ))
#earth
# degree=[1]; nprune=2 [9] 17 25 33; RMSE=0.1334478
#gbm
# shrinkage=0.05 [0.10] 0.15 0.20 0.25; n.trees=100 150 200 [250] 300; interaction.depth=[1] 2 3 4 5; n.minobsinnode=[10]; RMSE=0.2008313
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "gbm", parameter = "shrinkage", min = 0.05, max = 0.25, by = 0.05)
# ,data.frame(method = "gbm", parameter = "n.trees", min = 100, max = 300, by = 50)
# ,data.frame(method = "gbm", parameter = "interaction.depth", min = 1, max = 5, by = 1)
# ,data.frame(method = "gbm", parameter = "n.minobsinnode", min = 10, max = 10, by = 10)
# #seq(from=0.05, to=0.25, by=0.05)
# ))
#glmnet
# alpha=0.100 [0.325] 0.550 0.775 1.000; lambda=0.0005232693 0.0024288010 0.0112734954 [0.0523269304] 0.2428800957; RMSE=0.6164891
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "glmnet", parameter = "alpha", vals = "0.550 0.775 0.8875 0.94375 1.000")
# ,data.frame(method = "glmnet", parameter = "lambda", vals = "9.858855e-05 0.0001971771 0.0009152152 0.0042480525 0.0197177130")
# ))
#nnet
# size=3 5 [7] 9 11; decay=0.0001 0.001 0.01 [0.1] 0.2; RMSE=0.9287422
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "nnet", parameter = "size", vals = "3 5 7 9 11")
# ,data.frame(method = "nnet", parameter = "decay", vals = "0.0001 0.0010 0.0100 0.1000 0.2000")
# ))
#rf # Don't bother; results are not deterministic
# mtry=2 35 68 [101] 134; RMSE=0.1339974
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "rf", parameter = "mtry", vals = "2 5 9 13 17")
# ))
#rpart
# cp=0.020 [0.025] 0.030 0.035 0.040; RMSE=0.1770237
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "rpart", parameter = "cp", vals = "0.004347826 0.008695652 0.017391304 0.021739130 0.034782609")
# ))
#svmLinear
# C=0.01 0.05 [0.10] 0.50 1.00 2.00 3.00 4.00; RMSE=0.1271318; 0.1296718
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "svmLinear", parameter = "C", vals = "0.01 0.05 0.1 0.5 1")
# ))
#svmLinear2
# cost=0.0625 0.1250 [0.25] 0.50 1.00; RMSE=0.1276354
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "svmLinear2", parameter = "cost", vals = "0.0625 0.125 0.25 0.5 1")
# ))
#svmPoly
# degree=[1] 2 3 4 5; scale=0.01 0.05 [0.1] 0.5 1; C=0.50 1.00 [2.00] 3.00 4.00; RMSE=0.1276130
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method="svmPoly", parameter="degree", min=1, max=5, by=1) #seq(1, 5, 1)
# ,data.frame(method="svmPoly", parameter="scale", vals="0.01, 0.05, 0.1, 0.5, 1")
# ,data.frame(method="svmPoly", parameter="C", vals="0.50, 1.00, 2.00, 3.00, 4.00")
# ))
#svmRadial
# sigma=[0.08674323]; C=0.25 0.50 1.00 [2.00] 4.00; RMSE=0.1614957
#glb2Sav(); all.equal(sav_models_df, glb_models_df)
glb_preproc_methods <- NULL
# c("YeoJohnson", "center.scale", "range", "pca", "ica", "spatialSign")
# Baseline prediction model feature(s)
glb_Baseline_mdl_var <- NULL # or c("<feat>")
glbMdlMetric_terms <- NULL # or matrix(c(
# 0,1,2,3,4,
# 2,0,1,2,3,
# 4,2,0,1,2,
# 6,4,2,0,1,
# 8,6,4,2,0
# ), byrow=TRUE, nrow=5)
glbMdlMetricSummary <- NULL # or "<metric_name>"
glbMdlMetricMaximize <- NULL # or FALSE (TRUE is not the default for both classification & regression)
glbMdlMetricSummaryFn <- NULL # or function(data, lev=NULL, model=NULL) {
# confusion_mtrx <- t(as.matrix(confusionMatrix(data$pred, data$obs)))
# #print(confusion_mtrx)
# #print(confusion_mtrx * glbMdlMetric_terms)
# metric <- sum(confusion_mtrx * glbMdlMetric_terms) / nrow(data)
# names(metric) <- glbMdlMetricSummary
# return(metric)
# }
glbMdlCheckRcv <- FALSE # Turn it on when needed; otherwise takes long time
glb_rcv_n_folds <- 3 # or NULL
glb_rcv_n_repeats <- 3 # or NULL
glb_clf_proba_threshold <- NULL # 0.5
# Model selection criteria
if (glb_is_regression)
glbMdlMetricsEval <- c("min.RMSE.OOB", "max.R.sq.OOB", "max.Adj.R.sq.fit", "min.RMSE.fit")
#glbMdlMetricsEval <- c("min.RMSE.fit", "max.R.sq.fit", "max.Adj.R.sq.fit")
if (glb_is_classification) {
if (glb_is_binomial)
glbMdlMetricsEval <-
c("max.Accuracy.OOB", "max.AUCROCR.OOB", "max.AUCpROC.OOB", "min.aic.fit", "max.Accuracy.fit") else
glbMdlMetricsEval <- c("max.Accuracy.OOB", "max.Kappa.OOB")
}
# select from NULL [no ensemble models], "auto" [all models better than MFO or Baseline], c(mdl_ids in glb_models_lst) [Typically top-rated models in auto]
glb_mdl_ensemble <- NULL
# "%<d-% setdiff(mygetEnsembleAutoMdlIds(), 'CSM.X.rf')"
# c(<comma-separated-mdlIds>
# )
# Only for classifications; for regressions remove "(.*)\\.prob" form the regex
# tmp_fitobs_df <- glbObsFit[, grep(paste0("^", gsub(".", "\\.", mygetPredictIds$value, fixed = TRUE), "CSM\\.X\\.(.*)\\.prob"), names(glbObsFit), value = TRUE)]; cor_mtrx <- cor(tmp_fitobs_df); cor_vctr <- sort(cor_mtrx[row.names(orderBy(~-Overall, varImp(glb_models_lst[["Ensemble.repeatedcv.glmnet"]])$imp))[1], ]); summary(cor_vctr); cor_vctr
#ntv.glm <- glm(reformulate(indepVar, glb_rsp_var), family = "binomial", data = glbObsFit)
#step.glm <- step(ntv.glm)
glbMdlSelId <- "All.X##rcv#glmnet" #select from c(NULL, "All.X##rcv#glmnet", "RFE.X##rcv#glmnet", <mdlId>)
glbMdlFinId <- NULL #select from c(NULL, glbMdlSelId)
glb_dsp_cols <- c(".pos", glbFeatsId, glbFeatsCategory, glb_rsp_var
# List critical cols excl. above
)
# Output specs
# lclgetfltout_df <- function(obsOutFinDf) {
# require(tidyr)
# obsOutFinDf <- obsOutFinDf %>%
# tidyr::separate("ImageId.x.y", c(".src", ".pos", "x", "y"),
# sep = "#", remove = TRUE, extra = "merge")
# # mnm prefix stands for max_n_mean
# mnmout_df <- obsOutFinDf %>%
# dplyr::group_by(.pos) %>%
# #dplyr::top_n(1, Probability1) %>% # Score = 3.9426
# #dplyr::top_n(2, Probability1) %>% # Score = ???; weighted = 3.94254;
# #dplyr::top_n(3, Probability1) %>% # Score = 3.9418; weighted = 3.94169;
# dplyr::top_n(4, Probability1) %>% # Score = ???; weighted = 3.94149;
# #dplyr::top_n(5, Probability1) %>% # Score = 3.9421; weighted = 3.94178
#
# # dplyr::summarize(xMeanN = mean(as.numeric(x)), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), Probability1), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1, 0.2357323, 0.2336925)), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1)), yMeanN = mean(as.numeric(y)))
# dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1)),
# yMeanN = weighted.mean(as.numeric(y), c(Probability1)))
#
# maxout_df <- obsOutFinDf %>%
# dplyr::group_by(.pos) %>%
# dplyr::summarize(maxProb1 = max(Probability1))
# fltout_df <- merge(maxout_df, obsOutFinDf,
# by.x = c(".pos", "maxProb1"), by.y = c(".pos", "Probability1"),
# all.x = TRUE)
# fmnout_df <- merge(fltout_df, mnmout_df,
# by.x = c(".pos"), by.y = c(".pos"),
# all.x = TRUE)
# return(fmnout_df)
# }
glbObsOut <- list(NULL
# glbFeatsId will be the first output column, by default
,vars = list()
# ,mapFn = function(obsOutFinDf) {
# }
)
#obsOutFinDf <- savobsOutFinDf
# glbObsOut$mapFn <- function(obsOutFinDf) {
# txfout_df <- dplyr::select(obsOutFinDf, -.pos.y) %>%
# dplyr::mutate(
# lunch = levels(glbObsTrn[, "lunch" ])[
# round(mean(as.numeric(glbObsTrn[, "lunch" ])), 0)],
# dinner = levels(glbObsTrn[, "dinner" ])[
# round(mean(as.numeric(glbObsTrn[, "dinner" ])), 0)],
# reserve = levels(glbObsTrn[, "reserve" ])[
# round(mean(as.numeric(glbObsTrn[, "reserve" ])), 0)],
# outdoor = levels(glbObsTrn[, "outdoor" ])[
# round(mean(as.numeric(glbObsTrn[, "outdoor" ])), 0)],
# expensive = levels(glbObsTrn[, "expensive"])[
# round(mean(as.numeric(glbObsTrn[, "expensive"])), 0)],
# liquor = levels(glbObsTrn[, "liquor" ])[
# round(mean(as.numeric(glbObsTrn[, "liquor" ])), 0)],
# table = levels(glbObsTrn[, "table" ])[
# round(mean(as.numeric(glbObsTrn[, "table" ])), 0)],
# classy = levels(glbObsTrn[, "classy" ])[
# round(mean(as.numeric(glbObsTrn[, "classy" ])), 0)],
# kids = levels(glbObsTrn[, "kids" ])[
# round(mean(as.numeric(glbObsTrn[, "kids" ])), 0)]
# )
#
# print("ObsNew output class tables:")
# print(sapply(c("lunch","dinner","reserve","outdoor",
# "expensive","liquor","table",
# "classy","kids"),
# function(feat) table(txfout_df[, feat], useNA = "ifany")))
#
# txfout_df <- txfout_df %>%
# dplyr::mutate(labels = "") %>%
# dplyr::mutate(labels =
# ifelse(lunch != "-1", paste(labels, lunch ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(dinner != "-1", paste(labels, dinner ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(reserve != "-1", paste(labels, reserve ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(outdoor != "-1", paste(labels, outdoor ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(expensive != "-1", paste(labels, expensive), labels)) %>%
# dplyr::mutate(labels =
# ifelse(liquor != "-1", paste(labels, liquor ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(table != "-1", paste(labels, table ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(classy != "-1", paste(labels, classy ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(kids != "-1", paste(labels, kids ), labels)) %>%
# dplyr::select(business_id, labels)
# return(txfout_df)
# }
#if (!is.null(glbObsOut$mapFn)) obsOutFinDf <- glbObsOut$mapFn(obsOutFinDf); print(head(obsOutFinDf))
glb_out_obs <- NULL # select from c(NULL : default to "new", "all", "new", "trn")
if (glb_is_classification && glb_is_binomial) {
# glbObsOut$vars[["Probability1"]] <-
# "%<d-% glbObsNew[, mygetPredictIds(glb_rsp_var, glbMdlFinId)$prob]"
# glbObsOut$vars[[glb_rsp_var_raw]] <-
# "%<d-% glb_map_rsp_var_to_raw(glbObsNew[,
# mygetPredictIds(glb_rsp_var, glbMdlFinId)$value])"
glbObsOut$vars[["Predictions"]] <-
"%<d-% glb_map_rsp_var_to_raw(glbObsNew[,
mygetPredictIds(glb_rsp_var, glbMdlFinId)$value])"
} else {
# glbObsOut$vars[[glbFeatsId]] <-
# "%<d-% as.integer(gsub('Test#', '', glbObsNew[, glbFeatsId]))"
glbObsOut$vars[[glb_rsp_var]] <-
"%<d-% glbObsNew[, mygetPredictIds(glb_rsp_var, glbMdlFinId)$value]"
# for (outVar in setdiff(glbFeatsExcludeLcl, glb_rsp_var_raw))
# glbObsOut$vars[[outVar]] <-
# paste0("%<d-% mean(glbObsAll[, \"", outVar, "\"], na.rm = TRUE)")
}
# glbObsOut$vars[[glb_rsp_var_raw]] <- glb_rsp_var_raw
# glbObsOut$vars[[paste0(head(unlist(strsplit(mygetPredictIds$value, "")), -1), collapse = "")]] <-
glbOutStackFnames <- NULL #: default
# c("ebayipads_txt_assoc1_out_bid1_stack.csv") # manual stack
# c("ebayipads_finmdl_bid1_out_nnet_1.csv") # universal stack
glbOut <- list(pfx = "Votes_Q_02_cnk_")
# lclImageSampleSeed <- 129
glbOutDataVizFname <- NULL # choose from c(NULL, "<projectId>_obsall.csv")
glbChunks <- list(labels = c("set_global_options_wd","set_global_options"
,"import.data","inspect.data","scrub.data","transform.data"
,"extract.features"
,"extract.features.datetime","extract.features.image","extract.features.price"
,"extract.features.text","extract.features.string"
,"extract.features.end"
,"manage.missing.data","cluster.data","partition.data.training","select.features"
,"fit.models_0","fit.models_1","fit.models_2","fit.models_3"
,"fit.data.training_0","fit.data.training_1"
,"predict.data.new"
,"display.session.info"))
# To ensure that all chunks in this script are in glbChunks
if (!is.null(chkChunksLabels <- knitr::all_labels()) && # knitr::all_labels() doesn't work in console runs
!identical(chkChunksLabels, glbChunks$labels)) {
print(sprintf("setdiff(chkChunksLabels, glbChunks$labels): %s",
setdiff(chkChunksLabels, glbChunks$labels)))
print(sprintf("setdiff(glbChunks$labels, chkChunksLabels): %s",
setdiff(glbChunks$labels, chkChunksLabels)))
}
glbChunks[["first"]] <- "cluster.data" #default: script will load envir from previous chunk
glbChunks[["last"]] <- NULL #NULL #default: script will save envir at end of this chunk
#mysavChunk(glbOut$pfx, glbChunks[["last"]]) # called from myevlChunk
# Inspect max OOB FP
#chkObsOOB <- subset(glbObsOOB, !label.fctr.All.X..rcv.glmnet.is.acc)
#chkObsOOBFP <- subset(chkObsOOB, label.fctr.All.X..rcv.glmnet == "left_eye_center") %>% dplyr::mutate(Probability1 = label.fctr.All.X..rcv.glmnet.prob) %>% select(-.src, -.pos, -x, -y) %>% lclgetfltout_df() %>% mutate(obj.distance = (((as.numeric(x) - left_eye_center_x.int) ^ 2) + ((as.numeric(y) - left_eye_center_y.int) ^ 2)) ^ 0.5) %>% dplyr::top_n(5, obj.distance) %>% dplyr::top_n(5, -patch.cor)
#
#newImgObs <- glbObsNew[(glbObsNew$ImageId == "Test#0001"), ]; print(newImgObs[which.max(newImgObs$label.fctr.Final..rcv.glmnet.prob), ])
#OOBImgObs <- glbObsOOB[(glbObsOOB$ImageId == "Train#0003"), ]; print(OOBImgObs[which.max(OOBImgObs$label.fctr.All.X..rcv.glmnet.prob), ])
#load("Votes_Q_02_cnk_extract.features.end.RData", verbose = TRUE)
#mygetImage(which(glbObsAll[, glbFeatsId] == "Train#0003"), names(glbFeatsImage)[1], plot = TRUE, featHighlight = c("left_eye_center_x", "left_eye_center_y"), ovrlHighlight = c(66, 35))
# Depict process
glb_analytics_pn <- petrinet(name = "glb_analytics_pn",
trans_df = data.frame(id = 1:6,
name = c("data.training.all","data.new",
"model.selected","model.final",
"data.training.all.prediction","data.new.prediction"),
x=c( -5,-5,-15,-25,-25,-35),
y=c( -5, 5, 0, 0, -5, 5)
),
places_df=data.frame(id=1:4,
name=c("bgn","fit.data.training.all","predict.data.new","end"),
x=c( -0, -20, -30, -40),
y=c( 0, 0, 0, 0),
M0=c( 3, 0, 0, 0)
),
arcs_df = data.frame(
begin = c("bgn","bgn","bgn",
"data.training.all","model.selected","fit.data.training.all",
"fit.data.training.all","model.final",
"data.new","predict.data.new",
"data.training.all.prediction","data.new.prediction"),
end = c("data.training.all","data.new","model.selected",
"fit.data.training.all","fit.data.training.all","model.final",
"data.training.all.prediction","predict.data.new",
"predict.data.new","data.new.prediction",
"end","end")
))
#print(ggplot.petrinet(glb_analytics_pn))
print(ggplot.petrinet(glb_analytics_pn) + coord_flip())## Loading required package: grid
glb_analytics_avl_objs <- NULL
glb_chunks_df <- myadd_chunk(NULL,
ifelse(is.null(glbChunks$first), "import.data", glbChunks$first))## label step_major step_minor label_minor bgn end elapsed
## 1 cluster.data 1 0 0 9.076 NA NAStep 1.0: cluster data
chunk option: eval=
Step 1.0: cluster data
Step 1.0: cluster data
Step 1.0: cluster data
Step 1.0: cluster data
Step 1.0: cluster data
Step 1.0: cluster data
```{r extract.features.image, cache=FALSE, echo=FALSE, fig.height=5, fig.width=5, eval=myevlChunk(glbChunks, glbOut$pfx)}
Step 1.0: cluster data
Step 1.0: cluster data
Step 1.0: cluster data
Step 1.0: cluster data
Step 1.0: cluster data
Step 1.0: cluster data
```{r cluster.data, cache=FALSE, echo=FALSE, eval=myevlChunk(glbChunks, glbOut$pfx)}
## label step_major step_minor label_minor bgn end
## 1 cluster.data 1 0 0 9.076 10.296
## 2 partition.data.training 2 0 0 10.297 NA
## elapsed
## 1 1.22
## 2 NAStep 2.0: partition data training
## [1] "partition.data.training chunk: setup: elapsed: 0.00 secs"## Loading required package: sqldf## Loading required package: gsubfn## Loading required package: proto## Loading required package: RSQLite## Loading required package: DBI## Loading required package: tcltk## Loading required package: reshape2## [1] "partition.data.training chunk: strata_mtrx complete: elapsed: 1.21 secs"
## [1] "partition.data.training chunk: obs_freq_df complete: elapsed: 1.21 secs"## Loading required package: sampling##
## Attaching package: 'sampling'## The following object is masked from 'package:caret':
##
## cluster## [1] "lclgetMatrixCorrelation: duration: 39.244000 secs"
## [1] "cor of Fit vs. OOB: 1.0000"
## [1] "lclgetMatrixCorrelation: duration: 13.685000 secs"
## [1] "cor of New vs. OOB: 1.0000"
## [1] "lclgetMatrixCorrelation: duration: 49.386000 secs"
## [1] "cor of Fit vs. New: 1.0000"## [1] "partition.data.training chunk: Fit/OOB partition complete: elapsed: 104.49 secs"## Party.Democrat Party.Republican Party.NA
## NA NA 1392
## Fit 2360 2093 NA
## OOB 591 524 NA
## Party.Democrat Party.Republican Party.NA
## NA NA 1
## Fit 0.5299798 0.4700202 NA
## OOB 0.5300448 0.4699552 NA
## Q109244.fctr .n.Fit .n.OOB .n.Tst .freqRatio.Fit .freqRatio.OOB
## 2 No 1961 498 622 0.4403773 0.4466368
## 1 NA 1746 438 547 0.3920952 0.3928251
## 3 Yes 746 179 223 0.1675275 0.1605381
## .freqRatio.Tst
## 2 0.4468391
## 1 0.3929598
## 3 0.1602011## [1] "glbObsAll: "## [1] 6960 219## [1] "glbObsTrn: "## [1] 5568 219## [1] "glbObsFit: "## [1] 4453 218## [1] "glbObsOOB: "## [1] 1115 218## [1] "glbObsNew: "## [1] 1392 218## [1] "partition.data.training chunk: teardown: elapsed: 105.43 secs"## label step_major step_minor label_minor bgn
## 2 partition.data.training 2 0 0 10.297
## 3 select.features 3 0 0 115.764
## end elapsed
## 2 115.763 105.467
## 3 NA NAStep 3.0: select features
## [1] "cor(Q98059.fctr, Q98078.fctr)=0.7689"
## [1] "cor(Party.fctr, Q98059.fctr)=0.0172"
## [1] "cor(Party.fctr, Q98078.fctr)=0.0257"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q98059.fctr as highly correlated with Q98078.fctr## [1] "cor(Q99480.fctr, Q99581.fctr)=0.7660"
## [1] "cor(Party.fctr, Q99480.fctr)=-0.0344"
## [1] "cor(Party.fctr, Q99581.fctr)=-0.0104"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q99581.fctr as highly correlated with Q99480.fctr## [1] "cor(Q108855.fctr, Q108856.fctr)=0.7430"
## [1] "cor(Party.fctr, Q108855.fctr)=-0.0371"
## [1] "cor(Party.fctr, Q108856.fctr)=-0.0140"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q108856.fctr as highly correlated with Q108855.fctr## [1] "cor(Q122770.fctr, Q122771.fctr)=0.7379"
## [1] "cor(Party.fctr, Q122770.fctr)=-0.0195"
## [1] "cor(Party.fctr, Q122771.fctr)=-0.0348"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q122770.fctr as highly correlated with Q122771.fctr## [1] "cor(Q106272.fctr, Q106388.fctr)=0.7339"
## [1] "cor(Party.fctr, Q106272.fctr)=-0.0401"
## [1] "cor(Party.fctr, Q106388.fctr)=-0.0342"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q106388.fctr as highly correlated with Q106272.fctr## [1] "cor(Q100680.fctr, Q100689.fctr)=0.7292"
## [1] "cor(Party.fctr, Q100680.fctr)=0.0158"
## [1] "cor(Party.fctr, Q100689.fctr)=0.0257"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q100680.fctr as highly correlated with Q100689.fctr## [1] "cor(Q99480.fctr, Q99716.fctr)=0.7252"
## [1] "cor(Party.fctr, Q99480.fctr)=-0.0344"
## [1] "cor(Party.fctr, Q99716.fctr)=0.0209"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q99716.fctr as highly correlated with Q99480.fctr## [1] "cor(Q120472.fctr, Q120650.fctr)=0.7126"
## [1] "cor(Party.fctr, Q120472.fctr)=-0.0462"
## [1] "cor(Party.fctr, Q120650.fctr)=-0.0271"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q120650.fctr as highly correlated with Q120472.fctr## [1] "cor(Q98869.fctr, Q99480.fctr)=0.7084"
## [1] "cor(Party.fctr, Q98869.fctr)=-0.0277"
## [1] "cor(Party.fctr, Q99480.fctr)=-0.0344"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q98869.fctr as highly correlated with Q99480.fctr## [1] "cor(Q123464.fctr, Q123621.fctr)=0.7078"
## [1] "cor(Party.fctr, Q123464.fctr)=-0.0136"
## [1] "cor(Party.fctr, Q123621.fctr)=-0.0255"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q123464.fctr as highly correlated with Q123621.fctr## [1] "cor(Q108754.fctr, Q108855.fctr)=0.7005"
## [1] "cor(Party.fctr, Q108754.fctr)=-0.0081"
## [1] "cor(Party.fctr, Q108855.fctr)=-0.0371"## Warning in myfind_cor_features(feats_df = glb_feats_df, obs_df =
## glbObsTrn, : Identified Q108754.fctr as highly correlated with Q108855.fctr## cor.y exclude.as.feat cor.y.abs cor.high.X
## Q109244.fctr 0.1203812469 0 0.1203812469 <NA>
## Hhold.fctr 0.0511386673 0 0.0511386673 <NA>
## Edn.fctr 0.0359295351 0 0.0359295351 <NA>
## Q101163.fctr 0.0295046473 0 0.0295046473 <NA>
## Q100689.fctr 0.0256915080 0 0.0256915080 <NA>
## Q98078.fctr 0.0256516490 0 0.0256516490 <NA>
## Q99716.fctr 0.0209286674 0 0.0209286674 Q99480.fctr
## Q120379.fctr 0.0206291292 0 0.0206291292 <NA>
## Q121699.fctr 0.0196933075 0 0.0196933075 <NA>
## Q105840.fctr 0.0195569165 0 0.0195569165 <NA>
## Q113583.fctr 0.0191894717 0 0.0191894717 <NA>
## Q115195.fctr 0.0174522586 0 0.0174522586 <NA>
## Q102089.fctr 0.0174087944 0 0.0174087944 <NA>
## Q98059.fctr 0.0171637755 0 0.0171637755 Q98078.fctr
## Q114386.fctr 0.0168013326 0 0.0168013326 <NA>
## Q100680.fctr 0.0157762454 0 0.0157762454 Q100689.fctr
## Q108342.fctr 0.0151842510 0 0.0151842510 <NA>
## Q111848.fctr 0.0141099384 0 0.0141099384 <NA>
## YOB.Age.fctr 0.0129198495 0 0.0129198495 <NA>
## Q118892.fctr 0.0125250379 0 0.0125250379 <NA>
## Q102687.fctr 0.0120079165 0 0.0120079165 <NA>
## Q115390.fctr 0.0119300319 0 0.0119300319 <NA>
## Q119851.fctr 0.0093381833 0 0.0093381833 <NA>
## Q114517.fctr 0.0084741753 0 0.0084741753 <NA>
## Q120012.fctr 0.0084652930 0 0.0084652930 <NA>
## Q109367.fctr 0.0080456026 0 0.0080456026 <NA>
## Q114961.fctr 0.0079206587 0 0.0079206587 <NA>
## Q121700.fctr 0.0067756198 0 0.0067756198 <NA>
## Q124122.fctr 0.0061257448 0 0.0061257448 <NA>
## Q111220.fctr 0.0055758571 0 0.0055758571 <NA>
## Q113992.fctr 0.0041479796 0 0.0041479796 <NA>
## Q121011.fctr 0.0037329030 0 0.0037329030 <NA>
## Q106042.fctr 0.0032327194 0 0.0032327194 <NA>
## Q116448.fctr 0.0031731051 0 0.0031731051 <NA>
## Q116601.fctr 0.0022379241 0 0.0022379241 <NA>
## Q104996.fctr 0.0012202806 0 0.0012202806 <NA>
## Q102906.fctr 0.0011540297 0 0.0011540297 <NA>
## Q113584.fctr 0.0011387024 0 0.0011387024 <NA>
## Q108950.fctr 0.0010567028 0 0.0010567028 <NA>
## Q102674.fctr 0.0009759844 0 0.0009759844 <NA>
## Q103293.fctr 0.0005915534 0 0.0005915534 <NA>
## Q112478.fctr 0.0001517248 0 0.0001517248 <NA>
## Q114748.fctr -0.0008477228 0 0.0008477228 <NA>
## Q107491.fctr -0.0014031814 0 0.0014031814 <NA>
## Q100562.fctr -0.0017132769 0 0.0017132769 <NA>
## Q108617.fctr -0.0024119725 0 0.0024119725 <NA>
## Q100010.fctr -0.0024291540 0 0.0024291540 <NA>
## Q115602.fctr -0.0027844465 0 0.0027844465 <NA>
## Q116953.fctr -0.0029786716 0 0.0029786716 <NA>
## Q115610.fctr -0.0035255582 0 0.0035255582 <NA>
## Q106997.fctr -0.0041749086 0 0.0041749086 <NA>
## Q120978.fctr -0.0044187616 0 0.0044187616 <NA>
## Q112512.fctr -0.0056768212 0 0.0056768212 <NA>
## Q108343.fctr -0.0060665340 0 0.0060665340 <NA>
## Q96024.fctr -0.0069116541 0 0.0069116541 <NA>
## Q106389.fctr -0.0077498918 0 0.0077498918 <NA>
## .rnorm -0.0078039520 0 0.0078039520 <NA>
## Q108754.fctr -0.0080847764 0 0.0080847764 Q108855.fctr
## Q98578.fctr -0.0081164509 0 0.0081164509 <NA>
## Q101162.fctr -0.0099412952 0 0.0099412952 <NA>
## Q115777.fctr -0.0101315203 0 0.0101315203 <NA>
## Q99581.fctr -0.0103662478 0 0.0103662478 Q99480.fctr
## Q124742.fctr -0.0111642906 0 0.0111642906 <NA>
## Q116797.fctr -0.0112749656 0 0.0112749656 <NA>
## Q112270.fctr -0.0116157798 0 0.0116157798 <NA>
## YOB -0.0116828198 1 0.0116828198 <NA>
## Q118237.fctr -0.0117079669 0 0.0117079669 <NA>
## Q119650.fctr -0.0125645475 0 0.0125645475 <NA>
## Q111580.fctr -0.0132382335 0 0.0132382335 <NA>
## Q123464.fctr -0.0136140083 0 0.0136140083 Q123621.fctr
## Q117193.fctr -0.0138241599 0 0.0138241599 <NA>
## Q99982.fctr -0.0139727928 0 0.0139727928 <NA>
## Q108856.fctr -0.0140363785 0 0.0140363785 Q108855.fctr
## Q118233.fctr -0.0147269325 0 0.0147269325 <NA>
## Q102289.fctr -0.0155850393 0 0.0155850393 <NA>
## Q116197.fctr -0.0158561766 0 0.0158561766 <NA>
## Income.fctr -0.0159635458 0 0.0159635458 <NA>
## Q118232.fctr -0.0171321152 0 0.0171321152 <NA>
## Q120194.fctr -0.0172986920 0 0.0172986920 <NA>
## Q114152.fctr -0.0175013163 0 0.0175013163 <NA>
## Q122770.fctr -0.0194639697 0 0.0194639697 Q122771.fctr
## Q117186.fctr -0.0198853672 0 0.0198853672 <NA>
## Q105655.fctr -0.0198994078 0 0.0198994078 <NA>
## Q106993.fctr -0.0207428635 0 0.0207428635 <NA>
## Q119334.fctr -0.0226894034 0 0.0226894034 <NA>
## Q122120.fctr -0.0229287700 0 0.0229287700 <NA>
## Q116441.fctr -0.0237358205 0 0.0237358205 <NA>
## Q118117.fctr -0.0253544150 0 0.0253544150 <NA>
## Q123621.fctr -0.0255329743 0 0.0255329743 <NA>
## Q122769.fctr -0.0259739146 0 0.0259739146 <NA>
## Q120650.fctr -0.0270889067 0 0.0270889067 Q120472.fctr
## Q98869.fctr -0.0276734114 0 0.0276734114 Q99480.fctr
## .pos -0.0302037138 1 0.0302037138 <NA>
## USER_ID -0.0302304868 1 0.0302304868 <NA>
## Q107869.fctr -0.0304661021 0 0.0304661021 <NA>
## Q120014.fctr -0.0318620439 0 0.0318620439 <NA>
## Q115899.fctr -0.0324177950 0 0.0324177950 <NA>
## Q106388.fctr -0.0341579350 0 0.0341579350 Q106272.fctr
## Q99480.fctr -0.0344412239 0 0.0344412239 <NA>
## Q122771.fctr -0.0348421015 0 0.0348421015 <NA>
## Q108855.fctr -0.0370970211 0 0.0370970211 <NA>
## Q110740.fctr -0.0380691243 0 0.0380691243 <NA>
## Q106272.fctr -0.0400926462 0 0.0400926462 <NA>
## Q101596.fctr -0.0409784077 0 0.0409784077 <NA>
## Q116881.fctr -0.0416860293 0 0.0416860293 <NA>
## Q120472.fctr -0.0462030674 0 0.0462030674 <NA>
## Q98197.fctr -0.0549342527 0 0.0549342527 <NA>
## Q113181.fctr -0.0808753072 0 0.0808753072 <NA>
## Q115611.fctr -0.0904468203 0 0.0904468203 <NA>
## Gender.fctr -0.1027400851 0 0.1027400851 <NA>
## freqRatio percentUnique zeroVar nzv is.cor.y.abs.low
## Q109244.fctr 1.125916 0.05387931 FALSE FALSE FALSE
## Hhold.fctr 1.525094 0.12571839 FALSE FALSE FALSE
## Edn.fctr 1.392610 0.14367816 FALSE FALSE FALSE
## Q101163.fctr 1.327394 0.05387931 FALSE FALSE FALSE
## Q100689.fctr 1.029800 0.05387931 FALSE FALSE FALSE
## Q98078.fctr 1.266595 0.05387931 FALSE FALSE FALSE
## Q99716.fctr 1.328693 0.05387931 FALSE FALSE FALSE
## Q120379.fctr 1.046326 0.05387931 FALSE FALSE FALSE
## Q121699.fctr 1.507127 0.05387931 FALSE FALSE FALSE
## Q105840.fctr 1.275362 0.05387931 FALSE FALSE FALSE
## Q113583.fctr 1.102515 0.05387931 FALSE FALSE FALSE
## Q115195.fctr 1.065496 0.05387931 FALSE FALSE FALSE
## Q102089.fctr 1.055963 0.05387931 FALSE FALSE FALSE
## Q98059.fctr 1.493810 0.05387931 FALSE FALSE FALSE
## Q114386.fctr 1.092072 0.05387931 FALSE FALSE FALSE
## Q100680.fctr 1.102386 0.05387931 FALSE FALSE FALSE
## Q108342.fctr 1.048292 0.05387931 FALSE FALSE FALSE
## Q111848.fctr 1.113602 0.05387931 FALSE FALSE FALSE
## YOB.Age.fctr 1.005794 0.16163793 FALSE FALSE FALSE
## Q118892.fctr 1.347380 0.05387931 FALSE FALSE FALSE
## Q102687.fctr 1.256545 0.05387931 FALSE FALSE FALSE
## Q115390.fctr 1.150505 0.05387931 FALSE FALSE FALSE
## Q119851.fctr 1.244519 0.05387931 FALSE FALSE FALSE
## Q114517.fctr 1.183374 0.05387931 FALSE FALSE FALSE
## Q120012.fctr 1.047185 0.05387931 FALSE FALSE FALSE
## Q109367.fctr 1.008571 0.05387931 FALSE FALSE FALSE
## Q114961.fctr 1.250436 0.05387931 FALSE FALSE FALSE
## Q121700.fctr 1.708221 0.05387931 FALSE FALSE TRUE
## Q124122.fctr 1.412807 0.05387931 FALSE FALSE TRUE
## Q111220.fctr 1.262849 0.05387931 FALSE FALSE TRUE
## Q113992.fctr 1.267442 0.05387931 FALSE FALSE TRUE
## Q121011.fctr 1.153676 0.05387931 FALSE FALSE TRUE
## Q106042.fctr 1.247738 0.05387931 FALSE FALSE TRUE
## Q116448.fctr 1.161031 0.05387931 FALSE FALSE TRUE
## Q116601.fctr 1.394914 0.05387931 FALSE FALSE TRUE
## Q104996.fctr 1.173840 0.05387931 FALSE FALSE TRUE
## Q102906.fctr 1.053396 0.05387931 FALSE FALSE TRUE
## Q113584.fctr 1.212486 0.05387931 FALSE FALSE TRUE
## Q108950.fctr 1.103872 0.05387931 FALSE FALSE TRUE
## Q102674.fctr 1.073412 0.05387931 FALSE FALSE TRUE
## Q103293.fctr 1.122287 0.05387931 FALSE FALSE TRUE
## Q112478.fctr 1.113648 0.05387931 FALSE FALSE TRUE
## Q114748.fctr 1.051125 0.05387931 FALSE FALSE TRUE
## Q107491.fctr 1.419021 0.05387931 FALSE FALSE TRUE
## Q100562.fctr 1.217215 0.05387931 FALSE FALSE TRUE
## Q108617.fctr 1.390618 0.05387931 FALSE FALSE TRUE
## Q100010.fctr 1.268156 0.05387931 FALSE FALSE TRUE
## Q115602.fctr 1.322302 0.05387931 FALSE FALSE TRUE
## Q116953.fctr 1.039180 0.05387931 FALSE FALSE TRUE
## Q115610.fctr 1.359695 0.05387931 FALSE FALSE TRUE
## Q106997.fctr 1.177632 0.05387931 FALSE FALSE TRUE
## Q120978.fctr 1.131963 0.05387931 FALSE FALSE TRUE
## Q112512.fctr 1.299253 0.05387931 FALSE FALSE TRUE
## Q108343.fctr 1.064910 0.05387931 FALSE FALSE TRUE
## Q96024.fctr 1.144428 0.05387931 FALSE FALSE TRUE
## Q106389.fctr 1.341307 0.05387931 FALSE FALSE TRUE
## .rnorm 1.000000 100.00000000 FALSE FALSE FALSE
## Q108754.fctr 1.008090 0.05387931 FALSE FALSE FALSE
## Q98578.fctr 1.093556 0.05387931 FALSE FALSE FALSE
## Q101162.fctr 1.103229 0.05387931 FALSE FALSE FALSE
## Q115777.fctr 1.140288 0.05387931 FALSE FALSE FALSE
## Q99581.fctr 1.375000 0.05387931 FALSE FALSE FALSE
## Q124742.fctr 2.565379 0.05387931 FALSE FALSE FALSE
## Q116797.fctr 1.009589 0.05387931 FALSE FALSE FALSE
## Q112270.fctr 1.254284 0.05387931 FALSE FALSE FALSE
## YOB 1.027559 1.41882184 FALSE FALSE FALSE
## Q118237.fctr 1.088017 0.05387931 FALSE FALSE FALSE
## Q119650.fctr 1.456978 0.05387931 FALSE FALSE FALSE
## Q111580.fctr 1.024977 0.05387931 FALSE FALSE FALSE
## Q123464.fctr 1.326681 0.05387931 FALSE FALSE FALSE
## Q117193.fctr 1.140665 0.05387931 FALSE FALSE FALSE
## Q99982.fctr 1.339380 0.05387931 FALSE FALSE FALSE
## Q108856.fctr 1.080645 0.05387931 FALSE FALSE FALSE
## Q118233.fctr 1.199142 0.05387931 FALSE FALSE FALSE
## Q102289.fctr 1.033482 0.05387931 FALSE FALSE FALSE
## Q116197.fctr 1.073778 0.05387931 FALSE FALSE FALSE
## Income.fctr 1.256724 0.12571839 FALSE FALSE FALSE
## Q118232.fctr 1.365812 0.05387931 FALSE FALSE FALSE
## Q120194.fctr 1.016716 0.05387931 FALSE FALSE FALSE
## Q114152.fctr 1.027617 0.05387931 FALSE FALSE FALSE
## Q122770.fctr 1.008802 0.05387931 FALSE FALSE FALSE
## Q117186.fctr 1.053878 0.05387931 FALSE FALSE FALSE
## Q105655.fctr 1.079316 0.05387931 FALSE FALSE FALSE
## Q106993.fctr 1.327392 0.05387931 FALSE FALSE FALSE
## Q119334.fctr 1.081498 0.05387931 FALSE FALSE FALSE
## Q122120.fctr 1.297443 0.05387931 FALSE FALSE FALSE
## Q116441.fctr 1.019645 0.05387931 FALSE FALSE FALSE
## Q118117.fctr 1.174006 0.05387931 FALSE FALSE FALSE
## Q123621.fctr 1.466381 0.05387931 FALSE FALSE FALSE
## Q122769.fctr 1.060606 0.05387931 FALSE FALSE FALSE
## Q120650.fctr 1.896247 0.05387931 FALSE FALSE FALSE
## Q98869.fctr 1.080860 0.05387931 FALSE FALSE FALSE
## .pos 1.000000 100.00000000 FALSE FALSE FALSE
## USER_ID 1.000000 100.00000000 FALSE FALSE FALSE
## Q107869.fctr 1.211050 0.05387931 FALSE FALSE FALSE
## Q120014.fctr 1.044944 0.05387931 FALSE FALSE FALSE
## Q115899.fctr 1.197849 0.05387931 FALSE FALSE FALSE
## Q106388.fctr 1.065033 0.05387931 FALSE FALSE FALSE
## Q99480.fctr 1.225404 0.05387931 FALSE FALSE FALSE
## Q122771.fctr 1.414753 0.05387931 FALSE FALSE FALSE
## Q108855.fctr 1.273980 0.05387931 FALSE FALSE FALSE
## Q110740.fctr 1.050779 0.05387931 FALSE FALSE FALSE
## Q106272.fctr 1.116536 0.05387931 FALSE FALSE FALSE
## Q101596.fctr 1.041667 0.05387931 FALSE FALSE FALSE
## Q116881.fctr 1.010066 0.05387931 FALSE FALSE FALSE
## Q120472.fctr 1.292633 0.05387931 FALSE FALSE FALSE
## Q98197.fctr 1.129371 0.05387931 FALSE FALSE FALSE
## Q113181.fctr 1.006354 0.05387931 FALSE FALSE FALSE
## Q115611.fctr 1.194859 0.05387931 FALSE FALSE FALSE
## Gender.fctr 1.561033 0.05387931 FALSE FALSE FALSE## Warning in myplot_scatter(plt_feats_df, "percentUnique", "freqRatio",
## colorcol_name = "nzv", : converting nzv to class:factor## Warning: Removed 3 rows containing missing values (geom_point).
## Warning: Removed 3 rows containing missing values (geom_point).
## Warning: Removed 3 rows containing missing values (geom_point).
## [1] cor.y exclude.as.feat cor.y.abs cor.high.X
## [5] freqRatio percentUnique zeroVar nzv
## [9] is.cor.y.abs.low
## <0 rows> (or 0-length row.names)## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.
## [1] "numeric data missing in glbObsAll: "
## YOB Party.fctr
## 415 1392
## [1] "numeric data w/ 0s in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ Infs in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ NaNs in glbObsAll: "
## named integer(0)
## [1] "string data missing in glbObsAll: "
## Gender Income HouseholdStatus EducationLevel
## 143 1273 552 1067
## Party Q124742 Q124122 Q123464
## NA 4340 3114 2912
## Q123621 Q122769 Q122770 Q122771
## 3018 2778 2597 2579
## Q122120 Q121699 Q121700 Q120978
## 2552 2279 2328 2303
## Q121011 Q120379 Q120650 Q120472
## 2256 2361 2283 2433
## Q120194 Q120012 Q120014 Q119334
## 2603 2344 2571 2477
## Q119851 Q119650 Q118892 Q118117
## 2243 2374 2206 2342
## Q118232 Q118233 Q118237 Q117186
## 3018 2659 2592 2845
## Q117193 Q116797 Q116881 Q116953
## 2799 2771 2889 2848
## Q116601 Q116441 Q116448 Q116197
## 2606 2684 2730 2657
## Q115602 Q115777 Q115610 Q115611
## 2619 2785 2637 2443
## Q115899 Q115390 Q114961 Q114748
## 2789 2860 2687 2462
## Q115195 Q114517 Q114386 Q113992
## 2647 2567 2686 2502
## Q114152 Q113583 Q113584 Q113181
## 2829 2632 2654 2576
## Q112478 Q112512 Q112270 Q111848
## 2790 2676 2820 2449
## Q111580 Q111220 Q110740 Q109367
## 2686 2563 2479 2624
## Q108950 Q109244 Q108855 Q108617
## 2641 2731 3008 2696
## Q108856 Q108754 Q108342 Q108343
## 3007 2770 2760 2736
## Q107869 Q107491 Q106993 Q106997
## 2762 2667 2676 2702
## Q106272 Q106388 Q106389 Q106042
## 2722 2818 2871 2762
## Q105840 Q105655 Q104996 Q103293
## 2876 2612 2620 2674
## Q102906 Q102674 Q102687 Q102289
## 2840 2864 2712 2790
## Q102089 Q101162 Q101163 Q101596
## 2736 2816 2995 2824
## Q100689 Q100680 Q100562 Q99982
## 2568 2787 2793 2871
## Q100010 Q99716 Q99581 Q99480
## 2688 2790 2690 2700
## Q98869 Q98578 Q98059 Q98078
## 2906 2867 2629 2945
## Q98197 Q96024 .lcn
## 2836 2858 1392## [1] "glb_feats_df:"## [1] 110 12## id exclude.as.feat rsp_var
## Party.fctr Party.fctr TRUE TRUE## id cor.y exclude.as.feat cor.y.abs cor.high.X
## USER_ID USER_ID -0.03023049 TRUE 0.03023049 <NA>
## Party.fctr Party.fctr NA TRUE NA <NA>
## freqRatio percentUnique zeroVar nzv is.cor.y.abs.low
## USER_ID 1 100 FALSE FALSE FALSE
## Party.fctr NA NA NA NA NA
## interaction.feat shapiro.test.p.value rsp_var_raw id_var
## USER_ID NA NA FALSE TRUE
## Party.fctr NA NA NA NA
## rsp_var
## USER_ID NA
## Party.fctr TRUE## [1] "glb_feats_df vs. glbObsAll: "## character(0)## [1] "glbObsAll vs. glb_feats_df: "## character(0)## label step_major step_minor label_minor bgn end
## 3 select.features 3 0 0 115.764 121.782
## 4 fit.models 4 0 0 121.782 NA
## elapsed
## 3 6.018
## 4 NAStep 4.0: fit models
fit.models_0_chunk_df <- myadd_chunk(NULL, "fit.models_0_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_0_bgn 1 0 setup 122.28 NA NA# load(paste0(glbOut$pfx, "dsk.RData"))
get_model_sel_frmla <- function() {
model_evl_terms <- c(NULL)
# min.aic.fit might not be avl
lclMdlEvlCriteria <-
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)]
for (metric in lclMdlEvlCriteria)
model_evl_terms <- c(model_evl_terms,
ifelse(length(grep("max", metric)) > 0, "-", "+"), metric)
if (glb_is_classification && glb_is_binomial)
model_evl_terms <- c(model_evl_terms, "-", "opt.prob.threshold.OOB")
model_sel_frmla <- as.formula(paste(c("~ ", model_evl_terms), collapse = " "))
return(model_sel_frmla)
}
get_dsp_models_df <- function() {
dsp_models_cols <- c("id",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
dsp_models_df <-
#orderBy(get_model_sel_frmla(), glb_models_df)[, c("id", glbMdlMetricsEval)]
orderBy(get_model_sel_frmla(), glb_models_df)[, dsp_models_cols]
nCvMdl <- sapply(glb_models_lst, function(mdl) nrow(mdl$results))
nParams <- sapply(glb_models_lst, function(mdl) ifelse(mdl$method == "custom", 0,
nrow(subset(modelLookup(mdl$method), parameter != "parameter"))))
# nCvMdl <- nCvMdl[names(nCvMdl) != "avNNet"]
# nParams <- nParams[names(nParams) != "avNNet"]
if (length(cvMdlProblems <- nCvMdl[nCvMdl <= nParams]) > 0) {
print("Cross Validation issues:")
warning("Cross Validation issues:")
print(cvMdlProblems)
}
pltMdls <- setdiff(names(nCvMdl), names(cvMdlProblems))
pltMdls <- setdiff(pltMdls, names(nParams[nParams == 0]))
# length(pltMdls) == 21
png(paste0(glbOut$pfx, "bestTune.png"), width = 480 * 2, height = 480 * 4)
grid.newpage()
pushViewport(viewport(layout = grid.layout(ceiling(length(pltMdls) / 2.0), 2)))
pltIx <- 1
for (mdlId in pltMdls) {
print(ggplot(glb_models_lst[[mdlId]], highBestTune = TRUE) + labs(title = mdlId),
vp = viewport(layout.pos.row = ceiling(pltIx / 2.0),
layout.pos.col = ((pltIx - 1) %% 2) + 1))
pltIx <- pltIx + 1
}
dev.off()
if (all(row.names(dsp_models_df) != dsp_models_df$id))
row.names(dsp_models_df) <- dsp_models_df$id
return(dsp_models_df)
}
#get_dsp_models_df()
if (glb_is_classification && glb_is_binomial &&
(length(unique(glbObsFit[, glb_rsp_var])) < 2))
stop("glbObsFit$", glb_rsp_var, ": contains less than 2 unique values: ",
paste0(unique(glbObsFit[, glb_rsp_var]), collapse=", "))
max_cor_y_x_vars <- orderBy(~ -cor.y.abs,
subset(glb_feats_df, (exclude.as.feat == 0) & !nzv & !is.cor.y.abs.low &
is.na(cor.high.X)))[1:2, "id"]
max_cor_y_x_vars <- max_cor_y_x_vars[!is.na(max_cor_y_x_vars)]
if (length(max_cor_y_x_vars) < 2)
max_cor_y_x_vars <- union(max_cor_y_x_vars, ".pos")
if (!is.null(glb_Baseline_mdl_var)) {
if ((max_cor_y_x_vars[1] != glb_Baseline_mdl_var) &
(glb_feats_df[glb_feats_df$id == max_cor_y_x_vars[1], "cor.y.abs"] >
glb_feats_df[glb_feats_df$id == glb_Baseline_mdl_var, "cor.y.abs"]))
stop(max_cor_y_x_vars[1], " has a higher correlation with ", glb_rsp_var,
" than the Baseline var: ", glb_Baseline_mdl_var)
}
glb_model_type <- ifelse(glb_is_regression, "regression", "classification")
# Model specs
# c("id.prefix", "method", "type",
# # trainControl params
# "preProc.method", "cv.n.folds", "cv.n.repeats", "summary.fn",
# # train params
# "metric", "metric.maximize", "tune.df")
# Baseline
if (!is.null(glb_Baseline_mdl_var)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Baseline"), major.inc = FALSE,
label.minor = "mybaseln_classfr")
ret_lst <- myfit_mdl(mdl_id="Baseline",
model_method="mybaseln_classfr",
indepVar=glb_Baseline_mdl_var,
rsp_var=glb_rsp_var,
fit_df=glbObsFit, OOB_df=glbObsOOB)
}
# Most Frequent Outcome "MFO" model: mean(y) for regression
# Not using caret's nullModel since model stats not avl
# Cannot use rpart for multinomial classification since it predicts non-MFO
if (glb_is_classification) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "MFO"), major.inc = FALSE,
label.minor = "myMFO_classfr")
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "MFO", type = glb_model_type, trainControl.method = "none",
train.method = ifelse(glb_is_regression, "lm", "myMFO_classfr"))),
indepVar = ".rnorm", rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
# "random" model - only for classification;
# none needed for regression since it is same as MFO
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Random"), major.inc = FALSE,
label.minor = "myrandom_classfr")
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Random", type = glb_model_type, trainControl.method = "none",
train.method = "myrandom_classfr")),
indepVar = ".rnorm", rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}## label step_major step_minor label_minor bgn end
## 1 fit.models_0_bgn 1 0 setup 122.280 122.312
## 2 fit.models_0_MFO 1 1 myMFO_classfr 122.312 NA
## elapsed
## 1 0.032
## 2 NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: MFO###myMFO_classfr"
## [1] " indepVar: .rnorm"
## [1] "myfit_mdl: setup complete: 0.418000 secs"
## Fitting parameter = none on full training set
## [1] "in MFO.Classifier$fit"
## [1] "unique.vals:"
## [1] R D
## Levels: R D
## [1] "unique.prob:"
## y
## D R
## 0.5299798 0.4700202
## [1] "MFO.val:"
## [1] "D"
## [1] "myfit_mdl: train complete: 0.791000 secs"
## Length Class Mode
## unique.vals 2 factor numeric
## unique.prob 2 -none- numeric
## MFO.val 1 -none- character
## x.names 1 -none- character
## xNames 1 -none- character
## problemType 1 -none- character
## tuneValue 1 data.frame list
## obsLevels 2 -none- character
## [1] "myfit_mdl: train diagnostics complete: 0.793000 secs"## Loading required namespace: pROC## [1] "entr MFO.Classifier$predict"
## [1] "exit MFO.Classifier$predict"## Loading required package: ROCR## Loading required package: gplots##
## Attaching package: 'gplots'## The following object is masked from 'package:stats':
##
## lowess## [1] "in MFO.Classifier$prob"
## R D
## 1 0.5299798 0.4700202
## 2 0.5299798 0.4700202
## 3 0.5299798 0.4700202
## 4 0.5299798 0.4700202
## 5 0.5299798 0.4700202
## 6 0.5299798 0.4700202
## Prediction
## Reference R D
## R 2093 0
## D 2360 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.4700202 0.0000000 0.4552725 0.4848073 0.5299798
## AccuracyPValue McnemarPValue
## 1.0000000 0.0000000
## [1] "entr MFO.Classifier$predict"
## [1] "exit MFO.Classifier$predict"
## [1] "in MFO.Classifier$prob"
## R D
## 1 0.5299798 0.4700202
## 2 0.5299798 0.4700202
## 3 0.5299798 0.4700202
## 4 0.5299798 0.4700202
## 5 0.5299798 0.4700202
## 6 0.5299798 0.4700202
## Prediction
## Reference R D
## R 524 0
## D 591 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 4.699552e-01 0.000000e+00 4.403240e-01 4.997453e-01 5.300448e-01
## AccuracyPValue McnemarPValue
## 9.999739e-01 4.131000e-130
## [1] "myfit_mdl: predict complete: 4.995000 secs"
## id feats max.nTuningRuns min.elapsedtime.everything
## 1 MFO###myMFO_classfr .rnorm 0 0.362
## min.elapsedtime.final max.AUCpROC.fit max.Sens.fit max.Spec.fit
## 1 0.004 0.5 0 1
## max.AUCROCR.fit opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.5 0.5 0.6394745 0.4700202
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.4552725 0.4848073 0
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB max.AUCROCR.OOB
## 1 0.5 0 1 0.5
## opt.prob.threshold.OOB max.f.score.OOB max.Accuracy.OOB
## 1 0.5 0.6394143 0.4699552
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.440324 0.4997453 0
## [1] "myfit_mdl: exit: 5.004000 secs"
## label step_major step_minor label_minor bgn
## 2 fit.models_0_MFO 1 1 myMFO_classfr 122.312
## 3 fit.models_0_Random 1 2 myrandom_classfr 127.322
## end elapsed
## 2 127.321 5.01
## 3 NA NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Random###myrandom_classfr"
## [1] " indepVar: .rnorm"
## [1] "myfit_mdl: setup complete: 0.415000 secs"
## Fitting parameter = none on full training set
## [1] "myfit_mdl: train complete: 0.695000 secs"
## Length Class Mode
## unique.vals 2 factor numeric
## unique.prob 2 table numeric
## xNames 1 -none- character
## problemType 1 -none- character
## tuneValue 1 data.frame list
## obsLevels 2 -none- character
## [1] "myfit_mdl: train diagnostics complete: 0.696000 secs"
## [1] "in Random.Classifier$prob"
## Prediction
## Reference R D
## R 2093 0
## D 2360 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.4700202 0.0000000 0.4552725 0.4848073 0.5299798
## AccuracyPValue McnemarPValue
## 1.0000000 0.0000000
## [1] "in Random.Classifier$prob"
## Prediction
## Reference R D
## R 524 0
## D 591 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 4.699552e-01 0.000000e+00 4.403240e-01 4.997453e-01 5.300448e-01
## AccuracyPValue McnemarPValue
## 9.999739e-01 4.131000e-130
## [1] "myfit_mdl: predict complete: 6.269000 secs"
## id feats max.nTuningRuns
## 1 Random###myrandom_classfr .rnorm 0
## min.elapsedtime.everything min.elapsedtime.final max.AUCpROC.fit
## 1 0.273 0.002 0.4943556
## max.Sens.fit max.Spec.fit max.AUCROCR.fit opt.prob.threshold.fit
## 1 0.4620162 0.5266949 0.4989014 0.55
## max.f.score.fit max.Accuracy.fit max.AccuracyLower.fit
## 1 0.6394745 0.4700202 0.4552725
## max.AccuracyUpper.fit max.Kappa.fit max.AUCpROC.OOB max.Sens.OOB
## 1 0.4848073 0 0.5268661 0.5038168
## max.Spec.OOB max.AUCROCR.OOB opt.prob.threshold.OOB max.f.score.OOB
## 1 0.5499154 0.5178149 0.55 0.6394143
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.4699552 0.440324 0.4997453
## max.Kappa.OOB
## 1 0
## [1] "myfit_mdl: exit: 6.280000 secs"# Max.cor.Y
# Check impact of cv
# rpart is not a good candidate since caret does not optimize cp (only tuning parameter of rpart) well
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.rcv.*X*"), major.inc = FALSE,
label.minor = "glmnet")## label step_major step_minor label_minor
## 3 fit.models_0_Random 1 2 myrandom_classfr
## 4 fit.models_0_Max.cor.Y.rcv.*X* 1 3 glmnet
## bgn end elapsed
## 3 127.322 133.612 6.29
## 4 133.613 NA NAret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.rcv.1X1", type = glb_model_type, trainControl.method = "none",
train.method = "glmnet")),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Max.cor.Y.rcv.1X1###glmnet"
## [1] " indepVar: Q109244.fctr,Gender.fctr"
## [1] "myfit_mdl: setup complete: 0.677000 secs"## Loading required package: glmnet## Loading required package: Matrix## Loaded glmnet 2.0-5## Fitting alpha = 0.1, lambda = 0.00303 on full training set
## [1] "myfit_mdl: train complete: 1.411000 secs"
## Length Class Mode
## a0 64 -none- numeric
## beta 256 dgCMatrix S4
## df 64 -none- numeric
## dim 2 -none- numeric
## lambda 64 -none- numeric
## dev.ratio 64 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 4 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) Gender.fctrM Q109244.fctrNo Q109244.fctrYes
## 0.2976019 -0.2492304 -0.5460175 1.6311860
## [1] "max lambda < lambdaOpt:"
## [1] "Feats mismatch between coefs_left & rght:"
## [1] "(Intercept)" "Gender.fctrF" "Gender.fctrM" "Q109244.fctrNo"
## [5] "Q109244.fctrYes"
## [1] "myfit_mdl: train diagnostics complete: 1.514000 secs"
## Prediction
## Reference R D
## R 1994 99
## D 1713 647
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.930833e-01 2.173699e-01 5.784850e-01 6.075594e-01 5.299798e-01
## AccuracyPValue McnemarPValue
## 1.402069e-17 3.397523e-314
## Prediction
## Reference R D
## R 524 0
## D 591 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 4.699552e-01 0.000000e+00 4.403240e-01 4.997453e-01 5.300448e-01
## AccuracyPValue McnemarPValue
## 9.999739e-01 4.131000e-130
## [1] "myfit_mdl: predict complete: 5.562000 secs"
## id feats max.nTuningRuns
## 1 Max.cor.Y.rcv.1X1###glmnet Q109244.fctr,Gender.fctr 0
## min.elapsedtime.everything min.elapsedtime.final max.AUCpROC.fit
## 1 0.725 0.063 0.6195812
## max.Sens.fit max.Spec.fit max.AUCROCR.fit opt.prob.threshold.fit
## 1 0.5671285 0.6720339 0.3267482 0.6
## max.f.score.fit max.Accuracy.fit max.AccuracyLower.fit
## 1 0.6875862 0.5930833 0.578485
## max.AccuracyUpper.fit max.Kappa.fit max.AUCpROC.OOB max.Sens.OOB
## 1 0.6075594 0.2173699 0.4999322 0.4465649
## max.Spec.OOB max.AUCROCR.OOB opt.prob.threshold.OOB max.f.score.OOB
## 1 0.5532995 0.4910312 0.9 0.6394143
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.4699552 0.440324 0.4997453
## max.Kappa.OOB
## 1 0
## [1] "myfit_mdl: exit: 5.574000 secs"if (glbMdlCheckRcv) {
# rcv_n_folds == 1 & rcv_n_repeats > 1 crashes
for (rcv_n_folds in seq(3, glb_rcv_n_folds + 2, 2))
for (rcv_n_repeats in seq(1, glb_rcv_n_repeats + 2, 2)) {
# Experiment specific code to avoid caret crash
# lcl_tune_models_df <- rbind(data.frame()
# ,data.frame(method = "glmnet", parameter = "alpha",
# vals = "0.100 0.325 0.550 0.775 1.000")
# ,data.frame(method = "glmnet", parameter = "lambda",
# vals = "9.342e-02")
# )
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst =
list(
id.prefix = paste0("Max.cor.Y.rcv.", rcv_n_folds, "X", rcv_n_repeats),
type = glb_model_type,
# tune.df = lcl_tune_models_df,
trainControl.method = "repeatedcv",
trainControl.number = rcv_n_folds,
trainControl.repeats = rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.method = "glmnet", train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize)),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Add parallel coordinates graph of glb_models_df[, glbMdlMetricsEval] to evaluate cv parameters
tmp_models_cols <- c("id", "max.nTuningRuns",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
print(myplot_parcoord(obs_df = subset(glb_models_df,
grepl("Max.cor.Y.rcv.", id, fixed = TRUE),
select = -feats)[, tmp_models_cols],
id_var = "id"))
}
# Useful for stacking decisions
# fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
# paste0("fit.models_0_", "Max.cor.Y[rcv.1X1.cp.0|]"), major.inc = FALSE,
# label.minor = "rpart")
#
# ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
# id.prefix = "Max.cor.Y.rcv.1X1.cp.0", type = glb_model_type, trainControl.method = "none",
# train.method = "rpart",
# tune.df=data.frame(method="rpart", parameter="cp", min=0.0, max=0.0, by=0.1))),
# indepVar=max_cor_y_x_vars, rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB)
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
# if (glb_is_regression || glb_is_binomial) # For multinomials this model will be run next by default
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y",
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "rpart")),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Max.cor.Y##rcv#rpart"
## [1] " indepVar: Q109244.fctr,Gender.fctr"
## [1] "myfit_mdl: setup complete: 0.670000 secs"## Loading required package: rpart## Aggregating results
## Selecting tuning parameters
## Fitting cp = 0.0336 on full training set
## [1] "myfit_mdl: train complete: 2.200000 secs"## Loading required package: rpart.plot
## Call:
## rpart(formula = .outcome ~ ., control = list(minsplit = 20, minbucket = 7,
## cp = 0, maxcompete = 4, maxsurrogate = 5, usesurrogate = 2,
## surrogatestyle = 0, maxdepth = 30, xval = 0))
## n= 4453
##
## CP nsplit rel error
## 1 0.13425705 0 1.0000000
## 2 0.06306737 1 0.8657430
## 3 0.03356426 2 0.8026756
##
## Variable importance
## Q109244.fctrYes Q109244.fctrNo Gender.fctrM Gender.fctrF
## 82 15 1 1
##
## Node number 1: 4453 observations, complexity param=0.134257
## predicted class=D expected loss=0.4700202 P(node) =1
## class counts: 2093 2360
## probabilities: 0.470 0.530
## left son=2 (3707 obs) right son=3 (746 obs)
## Primary splits:
## Q109244.fctrYes < 0.5 to the left, improve=203.92180, (0 missing)
## Q109244.fctrNo < 0.5 to the right, improve=128.26260, (0 missing)
## Gender.fctrM < 0.5 to the right, improve= 33.63196, (0 missing)
## Gender.fctrF < 0.5 to the left, improve= 32.71833, (0 missing)
##
## Node number 2: 3707 observations, complexity param=0.06306737
## predicted class=R expected loss=0.4620987 P(node) =0.8324725
## class counts: 1994 1713
## probabilities: 0.538 0.462
## left son=4 (1961 obs) right son=5 (1746 obs)
## Primary splits:
## Q109244.fctrNo < 0.5 to the right, improve=37.829750, (0 missing)
## Gender.fctrM < 0.5 to the right, improve=11.923000, (0 missing)
## Gender.fctrF < 0.5 to the left, improve= 9.727259, (0 missing)
## Surrogate splits:
## Gender.fctrM < 0.5 to the right, agree=0.570, adj=0.088, (0 split)
## Gender.fctrF < 0.5 to the left, agree=0.564, adj=0.073, (0 split)
##
## Node number 3: 746 observations
## predicted class=D expected loss=0.1327078 P(node) =0.1675275
## class counts: 99 647
## probabilities: 0.133 0.867
##
## Node number 4: 1961 observations
## predicted class=R expected loss=0.3946966 P(node) =0.4403773
## class counts: 1187 774
## probabilities: 0.605 0.395
##
## Node number 5: 1746 observations
## predicted class=D expected loss=0.4621993 P(node) =0.3920952
## class counts: 807 939
## probabilities: 0.462 0.538
##
## n= 4453
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 4453 2093 D (0.4700202 0.5299798)
## 2) Q109244.fctrYes< 0.5 3707 1713 R (0.5379013 0.4620987)
## 4) Q109244.fctrNo>=0.5 1961 774 R (0.6053034 0.3946966) *
## 5) Q109244.fctrNo< 0.5 1746 807 D (0.4621993 0.5378007) *
## 3) Q109244.fctrYes>=0.5 746 99 D (0.1327078 0.8672922) *
## [1] "myfit_mdl: train diagnostics complete: 2.972000 secs"
## Prediction
## Reference R D
## R 1994 99
## D 1713 647
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 5.930833e-01 2.173699e-01 5.784850e-01 6.075594e-01 5.299798e-01
## AccuracyPValue McnemarPValue
## 1.402069e-17 3.397523e-314
## Prediction
## Reference R D
## R 524 0
## D 591 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 4.699552e-01 0.000000e+00 4.403240e-01 4.997453e-01 5.300448e-01
## AccuracyPValue McnemarPValue
## 9.999739e-01 4.131000e-130
## [1] "myfit_mdl: predict complete: 7.093000 secs"
## id feats max.nTuningRuns
## 1 Max.cor.Y##rcv#rpart Q109244.fctr,Gender.fctr 5
## min.elapsedtime.everything min.elapsedtime.final max.AUCpROC.fit
## 1 1.522 0.018 0.6195812
## max.Sens.fit max.Spec.fit max.AUCROCR.fit opt.prob.threshold.fit
## 1 0.5671285 0.6720339 0.3369762 0.55
## max.f.score.fit max.Accuracy.fit max.AccuracyLower.fit
## 1 0.6875862 0.6227314 0.578485
## max.AccuracyUpper.fit max.Kappa.fit max.AUCpROC.OOB max.Sens.OOB
## 1 0.6075594 0.2400193 0.4999322 0.4465649
## max.Spec.OOB max.AUCROCR.OOB opt.prob.threshold.OOB max.f.score.OOB
## 1 0.5532995 0.4999354 0.9 0.6394143
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.4699552 0.440324 0.4997453
## max.Kappa.OOB max.AccuracySD.fit max.KappaSD.fit
## 1 0 0.01420243 0.02887036
## [1] "myfit_mdl: exit: 7.107000 secs"if ((length(glbFeatsDateTime) > 0) &&
(sum(grepl(paste(names(glbFeatsDateTime), "\\.day\\.minutes\\.poly\\.", sep = ""),
names(glbObsAll))) > 0)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.Time.Poly"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars,
grep(paste(names(glbFeatsDateTime), "\\.day\\.minutes\\.poly\\.", sep = ""),
names(glbObsAll), value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Time.Poly",
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
if ((length(glbFeatsDateTime) > 0) &&
(sum(grepl(paste(names(glbFeatsDateTime), "\\.last[[:digit:]]", sep = ""),
names(glbObsAll))) > 0)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.Time.Lag"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars,
grep(paste(names(glbFeatsDateTime), "\\.last[[:digit:]]", sep = ""),
names(glbObsAll), value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Time.Lag",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
if (length(glbFeatsText) > 0) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Txt.*"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.(?!([T|P]\\.))", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.nonTP",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.T\\.", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.onlyT",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.P\\.", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.onlyP",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Interactions.High.cor.Y
if (length(int_feats <- setdiff(setdiff(unique(glb_feats_df$cor.high.X), NA),
subset(glb_feats_df, nzv)$id)) > 0) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Interact.High.cor.Y"), major.inc = FALSE,
label.minor = "glmnet")
ret_lst <- myfit_mdl(mdl_specs_lst=myinit_mdl_specs_lst(mdl_specs_lst=list(
id.prefix="Interact.High.cor.Y",
type=glb_model_type, trainControl.method="repeatedcv",
trainControl.number=glb_rcv_n_folds, trainControl.repeats=glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method="glmnet")),
indepVar=c(max_cor_y_x_vars, paste(max_cor_y_x_vars[1], int_feats, sep=":")),
rsp_var=glb_rsp_var,
fit_df=glbObsFit, OOB_df=glbObsOOB)
} ## label step_major step_minor label_minor
## 4 fit.models_0_Max.cor.Y.rcv.*X* 1 3 glmnet
## 5 fit.models_0_Interact.High.cor.Y 1 4 glmnet
## bgn end elapsed
## 4 133.613 146.332 12.719
## 5 146.332 NA NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Interact.High.cor.Y##rcv#glmnet"
## [1] " indepVar: Q109244.fctr,Gender.fctr,Q109244.fctr:Q99480.fctr,Q109244.fctr:Q98078.fctr,Q109244.fctr:Q100689.fctr,Q109244.fctr:Q108855.fctr,Q109244.fctr:Q123621.fctr,Q109244.fctr:Q122771.fctr,Q109244.fctr:Q120472.fctr,Q109244.fctr:Q106272.fctr"
## [1] "myfit_mdl: setup complete: 0.696000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.55, lambda = 0.00303 on full training set
## [1] "myfit_mdl: train complete: 6.035000 secs"
## Length Class Mode
## a0 72 -none- numeric
## beta 3744 dgCMatrix S4
## df 72 -none- numeric
## dim 2 -none- numeric
## lambda 72 -none- numeric
## dev.ratio 72 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 52 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) Gender.fctrM
## 0.30474474 -0.19235176
## Q109244.fctrNo Q109244.fctrYes
## -0.46779597 0.90303181
## Q109244.fctrNA:Q100689.fctrNo Q109244.fctrNo:Q100689.fctrNo
## 0.08937757 -0.12012631
## Q109244.fctrYes:Q100689.fctrNo Q109244.fctrNA:Q100689.fctrYes
## -0.03138994 0.35071312
## Q109244.fctrNo:Q100689.fctrYes Q109244.fctrYes:Q100689.fctrYes
## 0.05118867 0.39864211
## Q109244.fctrNA:Q106272.fctrNo Q109244.fctrNo:Q106272.fctrNo
## -0.05134160 0.06405302
## Q109244.fctrYes:Q106272.fctrNo Q109244.fctrNA:Q106272.fctrYes
## -0.08205810 -0.16747603
## Q109244.fctrYes:Q106272.fctrYes Q109244.fctrNA:Q108855.fctrUmm...
## 0.18585910 -0.16078900
## Q109244.fctrYes:Q108855.fctrUmm... Q109244.fctrNA:Q108855.fctrYes!
## 0.04539680 -0.13043743
## Q109244.fctrNo:Q108855.fctrYes! Q109244.fctrNo:Q120472.fctrArt
## -0.20995064 0.01730102
## Q109244.fctrYes:Q120472.fctrArt Q109244.fctrNA:Q120472.fctrScience
## 0.71571590 -0.11001508
## Q109244.fctrNo:Q120472.fctrScience Q109244.fctrYes:Q120472.fctrScience
## -0.07407132 -0.04959913
## Q109244.fctrYes:Q122771.fctrPc Q109244.fctrNA:Q122771.fctrPt
## 0.15205641 -0.25453650
## Q109244.fctrNo:Q122771.fctrPt Q109244.fctrYes:Q122771.fctrPt
## -0.23913386 -0.16063240
## Q109244.fctrNA:Q123621.fctrNo Q109244.fctrYes:Q123621.fctrNo
## -0.09400933 0.10314275
## Q109244.fctrNA:Q123621.fctrYes Q109244.fctrNo:Q123621.fctrYes
## -0.02524789 -0.11277084
## Q109244.fctrYes:Q123621.fctrYes Q109244.fctrNA:Q98078.fctrNo
## 0.07791017 0.25367620
## Q109244.fctrNo:Q98078.fctrNo Q109244.fctrYes:Q98078.fctrNo
## 0.12016433 0.15277814
## Q109244.fctrNA:Q98078.fctrYes Q109244.fctrYes:Q98078.fctrYes
## 0.18413697 0.33674598
## Q109244.fctrNA:Q99480.fctrNo Q109244.fctrNo:Q99480.fctrNo
## 0.29436751 0.37378839
## Q109244.fctrNA:Q99480.fctrYes Q109244.fctrNo:Q99480.fctrYes
## -0.28289751 -0.02938347
## [1] "max lambda < lambdaOpt:"
## (Intercept) Gender.fctrM
## 0.30665943 -0.19291421
## Q109244.fctrNo Q109244.fctrYes
## -0.47604533 0.91411986
## Q109244.fctrNA:Q100689.fctrNo Q109244.fctrNo:Q100689.fctrNo
## 0.09793173 -0.11545941
## Q109244.fctrYes:Q100689.fctrNo Q109244.fctrNA:Q100689.fctrYes
## -0.05251406 0.36007759
## Q109244.fctrNo:Q100689.fctrYes Q109244.fctrYes:Q100689.fctrYes
## 0.05953033 0.38676277
## Q109244.fctrNA:Q106272.fctrNo Q109244.fctrNo:Q106272.fctrNo
## -0.06156608 0.06654080
## Q109244.fctrYes:Q106272.fctrNo Q109244.fctrNA:Q106272.fctrYes
## -0.10686255 -0.17341318
## Q109244.fctrYes:Q106272.fctrYes Q109244.fctrNA:Q108855.fctrUmm...
## 0.17614268 -0.16629690
## Q109244.fctrYes:Q108855.fctrUmm... Q109244.fctrNA:Q108855.fctrYes!
## 0.04857188 -0.13404471
## Q109244.fctrNo:Q108855.fctrYes! Q109244.fctrNo:Q120472.fctrArt
## -0.21128031 0.02156135
## Q109244.fctrYes:Q120472.fctrArt Q109244.fctrNA:Q120472.fctrScience
## 0.70998060 -0.11193096
## Q109244.fctrNo:Q120472.fctrScience Q109244.fctrYes:Q120472.fctrScience
## -0.07337946 -0.07437396
## Q109244.fctrYes:Q122771.fctrPc Q109244.fctrNA:Q122771.fctrPt
## 0.14010536 -0.25858914
## Q109244.fctrNo:Q122771.fctrPt Q109244.fctrYes:Q122771.fctrPt
## -0.24120138 -0.18715985
## Q109244.fctrNA:Q123621.fctrNo Q109244.fctrYes:Q123621.fctrNo
## -0.09719484 0.13358947
## Q109244.fctrNA:Q123621.fctrYes Q109244.fctrNo:Q123621.fctrYes
## -0.02795962 -0.11513907
## Q109244.fctrYes:Q123621.fctrYes Q109244.fctrNA:Q98078.fctrNo
## 0.10598422 0.26284104
## Q109244.fctrNo:Q98078.fctrNo Q109244.fctrYes:Q98078.fctrNo
## 0.12389247 0.18077231
## Q109244.fctrNA:Q98078.fctrYes Q109244.fctrYes:Q98078.fctrYes
## 0.19266360 0.36290785
## Q109244.fctrNA:Q99480.fctrNo Q109244.fctrNo:Q99480.fctrNo
## 0.29259663 0.37381307
## Q109244.fctrNA:Q99480.fctrYes Q109244.fctrNo:Q99480.fctrYes
## -0.29170558 -0.03235030
## [1] "myfit_mdl: train diagnostics complete: 6.649000 secs"
## Prediction
## Reference R D
## R 1972 121
## D 1658 702
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.004940e-01 2.300879e-01 5.859338e-01 6.149224e-01 5.299798e-01
## AccuracyPValue McnemarPValue
## 1.612133e-21 2.297859e-290
## Prediction
## Reference R D
## R 524 0
## D 591 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 4.699552e-01 0.000000e+00 4.403240e-01 4.997453e-01 5.300448e-01
## AccuracyPValue McnemarPValue
## 9.999739e-01 4.131000e-130
## [1] "myfit_mdl: predict complete: 12.186000 secs"
## id
## 1 Interact.High.cor.Y##rcv#glmnet
## feats
## 1 Q109244.fctr,Gender.fctr,Q109244.fctr:Q99480.fctr,Q109244.fctr:Q98078.fctr,Q109244.fctr:Q100689.fctr,Q109244.fctr:Q108855.fctr,Q109244.fctr:Q123621.fctr,Q109244.fctr:Q122771.fctr,Q109244.fctr:Q120472.fctr,Q109244.fctr:Q106272.fctr
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 5.32 0.33
## max.AUCpROC.fit max.Sens.fit max.Spec.fit max.AUCROCR.fit
## 1 0.6372713 0.6364071 0.6381356 0.3046595
## opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.65 0.689149 0.6276719
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.5859338 0.6149224 0.2550614
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB max.AUCROCR.OOB
## 1 0.515779 0.5171756 0.5143824 0.4731743
## opt.prob.threshold.OOB max.f.score.OOB max.Accuracy.OOB
## 1 1 0.6394143 0.4699552
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.440324 0.4997453 0
## max.AccuracySD.fit max.KappaSD.fit
## 1 0.0127242 0.02650871
## [1] "myfit_mdl: exit: 12.200000 secs"# Low.cor.X
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Low.cor.X"), major.inc = FALSE,
label.minor = "glmnet")## label step_major step_minor label_minor
## 5 fit.models_0_Interact.High.cor.Y 1 4 glmnet
## 6 fit.models_0_Low.cor.X 1 5 glmnet
## bgn end elapsed
## 5 146.332 158.558 12.226
## 6 158.559 NA NAindepVar <- mygetIndepVar(glb_feats_df)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Low.cor.X",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Low.cor.X##rcv#glmnet"
## [1] " indepVar: Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr"
## [1] "myfit_mdl: setup complete: 0.692000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.1, lambda = 0.0652 on full training set
## [1] "myfit_mdl: train complete: 23.313000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Low.cor.X", : model's bestTune found at an extreme of
## tuneGrid for parameter: alpha## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Low.cor.X", : model's bestTune found at an extreme of
## tuneGrid for parameter: lambda
## Length Class Mode
## a0 91 -none- numeric
## beta 21112 dgCMatrix S4
## df 91 -none- numeric
## dim 2 -none- numeric
## lambda 91 -none- numeric
## dev.ratio 91 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 232 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) .rnorm Edn.fctr.L
## 0.2182238650 -0.0043218147 0.0889974083
## Edn.fctr^6 Edn.fctr^7 Gender.fctrF
## 0.0094799038 0.0048448375 0.0172572894
## Gender.fctrM Hhold.fctrMKy Hhold.fctrPKn
## -0.0954525253 -0.0787132143 0.4769245380
## Hhold.fctrSKy Income.fctr.Q Income.fctr.C
## 0.0943955021 -0.1221098223 -0.0659690797
## Q100689.fctrYes Q101163.fctrDad Q101163.fctrMom
## 0.0937319604 -0.1215446266 0.0660995478
## Q101596.fctrYes Q102089.fctrRent Q102687.fctrYes
## -0.0123450142 0.0406874879 0.0264877074
## Q104996.fctrNo Q104996.fctrYes Q105655.fctrYes
## -0.0337954466 0.0101901384 -0.0114351855
## Q105840.fctrNo Q105840.fctrYes Q106042.fctrNo
## -0.0123695990 0.0344623775 -0.0630096832
## Q106388.fctrYes Q106389.fctrNo Q106997.fctrGr
## -0.0188230968 -0.0340393517 -0.0364878723
## Q107869.fctrNo Q108342.fctrOnline Q108754.fctrYes
## 0.0044655353 0.0509099257 -0.0376620607
## Q108855.fctrYes! Q108856.fctrSocialize Q109244.fctrNo
## -0.0210268035 -0.0245883944 -0.4487227152
## Q109244.fctrYes Q109367.fctrYes Q110740.fctrPC
## 0.9786872953 0.0173930011 -0.0794727701
## Q111220.fctrNo Q111220.fctrYes Q111848.fctrYes
## -0.0033922528 0.0585611159 0.0457539270
## Q112478.fctrNo Q113181.fctrNo Q113181.fctrYes
## -0.0246349466 0.1112819023 -0.1476035076
## Q113583.fctrTunes Q113992.fctrYes Q114517.fctrNo
## 0.0154543164 0.0051559413 0.0291348877
## Q115195.fctrNo Q115195.fctrYes Q115390.fctrYes
## -0.0078804951 0.0287640101 0.0480452601
## Q115610.fctrNo Q115611.fctrNo Q115611.fctrYes
## -0.0222477010 0.1250266333 -0.2789081127
## Q115899.fctrCs Q115899.fctrMe Q116197.fctrA.M.
## 0.0716304093 -0.0260904021 -0.0174322339
## Q116881.fctrHappy Q116881.fctrRight Q116953.fctrNo
## 0.0169108547 -0.1579213060 -0.0631621922
## Q118117.fctrYes Q118232.fctrId Q118233.fctrNo
## -0.0334356195 0.1000892607 -0.0512886740
## Q118892.fctrNo Q119851.fctrNo Q119851.fctrYes
## -0.0085291598 -0.0732053282 0.0864474832
## Q120012.fctrYes Q120014.fctrNo Q120014.fctrYes
## 0.0271682299 0.0120135238 -0.0072627910
## Q120194.fctrStudy first Q120379.fctrNo Q120379.fctrYes
## 0.0016623595 -0.0288424701 0.0752754524
## Q120472.fctrScience Q120650.fctrNo Q121011.fctrNo
## -0.0747816069 0.0068796862 -0.0032091223
## Q121011.fctrYes Q121699.fctrYes Q122120.fctrYes
## 0.0005825808 0.0566692057 -0.0723720439
## Q122771.fctrPt Q124122.fctrNo Q124742.fctrNo
## -0.0931571736 -0.0136270820 0.0359290161
## Q96024.fctrNo Q98059.fctrOnly-child Q98059.fctrYes
## 0.0025316228 -0.0291527328 0.0386035110
## Q98197.fctrNo Q98197.fctrYes Q98869.fctrNo
## 0.1597329673 -0.1087430705 0.2515168378
## Q99480.fctrNo Q99480.fctrYes Q99716.fctrYes
## 0.1232352423 -0.0539966633 0.0532365742
## YOB.Age.fctr.L YOB.Age.fctr.C YOB.Age.fctr^4
## 0.1045001488 -0.0057348189 0.0094887582
## YOB.Age.fctr^7 YOB.Age.fctr^8
## -0.0613013716 -0.1099161376
## [1] "max lambda < lambdaOpt:"
## (Intercept) .rnorm Edn.fctr.L
## 0.221417216 -0.006597013 0.090650240
## Edn.fctr^4 Edn.fctr^6 Edn.fctr^7
## -0.006212844 0.014671948 0.012263535
## Gender.fctrF Gender.fctrM Hhold.fctrMKy
## 0.011870040 -0.097301759 -0.085045637
## Hhold.fctrPKn Hhold.fctrSKy Income.fctr.Q
## 0.494037561 0.105977265 -0.128755036
## Income.fctr.C Q100689.fctrYes Q101162.fctrPessimist
## -0.075857022 0.101220202 -0.002204401
## Q101163.fctrDad Q101163.fctrMom Q101596.fctrYes
## -0.126578407 0.067730099 -0.016968414
## Q102089.fctrRent Q102687.fctrYes Q102906.fctrYes
## 0.043669337 0.032907509 -0.007762629
## Q104996.fctrNo Q104996.fctrYes Q105655.fctrYes
## -0.037493190 0.015130905 -0.016975835
## Q105840.fctrNo Q105840.fctrYes Q106042.fctrNo
## -0.010171139 0.036925726 -0.066503426
## Q106388.fctrYes Q106389.fctrNo Q106997.fctrGr
## -0.022943776 -0.040627101 -0.043079556
## Q107869.fctrNo Q108342.fctrOnline Q108754.fctrYes
## 0.010479401 0.056696098 -0.044397972
## Q108855.fctrYes! Q108856.fctrSocialize Q109244.fctrNo
## -0.025021908 -0.031459608 -0.456280408
## Q109244.fctrYes Q109367.fctrYes Q110740.fctrMac
## 1.002758973 0.019318706 0.002156371
## Q110740.fctrPC Q111220.fctrNo Q111220.fctrYes
## -0.084754385 -0.007032618 0.064044977
## Q111848.fctrYes Q112270.fctrNo Q112478.fctrNo
## 0.052138649 0.003287377 -0.029376738
## Q113181.fctrNo Q113181.fctrYes Q113583.fctrTunes
## 0.112453535 -0.151021176 0.019871028
## Q113992.fctrYes Q114517.fctrNo Q115195.fctrNo
## 0.011251605 0.035545764 -0.011439291
## Q115195.fctrYes Q115390.fctrYes Q115610.fctrNo
## 0.031093303 0.054301606 -0.029943924
## Q115611.fctrNo Q115611.fctrYes Q115899.fctrCs
## 0.125263509 -0.286364102 0.077026205
## Q115899.fctrMe Q116197.fctrA.M. Q116881.fctrHappy
## -0.028044295 -0.024382405 0.021409011
## Q116881.fctrRight Q116953.fctrNo Q118117.fctrYes
## -0.161417346 -0.070435474 -0.035874178
## Q118232.fctrId Q118233.fctrNo Q118892.fctrNo
## 0.108484869 -0.058777096 -0.010341717
## Q119851.fctrNo Q119851.fctrYes Q120012.fctrYes
## -0.076983210 0.090596907 0.032055116
## Q120014.fctrNo Q120014.fctrYes Q120194.fctrStudy first
## 0.014190240 -0.009626995 0.005272177
## Q120379.fctrNo Q120379.fctrYes Q120472.fctrScience
## -0.032254122 0.081003638 -0.079944132
## Q120650.fctrNo Q121011.fctrNo Q121011.fctrYes
## 0.016571439 -0.004007171 0.002867060
## Q121699.fctrYes Q122120.fctrYes Q122771.fctrPt
## 0.061730344 -0.080375537 -0.101563391
## Q123621.fctrYes Q124122.fctrNo Q124742.fctrNo
## -0.005710537 -0.018809312 0.044885981
## Q96024.fctrNo Q98059.fctrOnly-child Q98059.fctrYes
## 0.007267349 -0.042172589 0.046420210
## Q98197.fctrNo Q98197.fctrYes Q98869.fctrNo
## 0.163217987 -0.111310168 0.261203168
## Q99480.fctrNo Q99480.fctrYes Q99716.fctrYes
## 0.127854410 -0.060882172 0.055399976
## YOB.Age.fctr.L YOB.Age.fctr.C YOB.Age.fctr^4
## 0.115326080 -0.015897589 0.014310212
## YOB.Age.fctr^7 YOB.Age.fctr^8
## -0.072623853 -0.121236319
## [1] "myfit_mdl: train diagnostics complete: 23.972000 secs"
## Prediction
## Reference R D
## R 1895 198
## D 1396 964
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.420391e-01 3.040295e-01 6.277567e-01 6.561349e-01 5.299798e-01
## AccuracyPValue McnemarPValue
## 8.008482e-52 1.722168e-197
## Prediction
## Reference R D
## R 524 0
## D 591 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 4.699552e-01 0.000000e+00 4.403240e-01 4.997453e-01 5.300448e-01
## AccuracyPValue McnemarPValue
## 9.999739e-01 4.131000e-130
## [1] "myfit_mdl: predict complete: 33.751000 secs"
## id
## 1 Low.cor.X##rcv#glmnet
## feats
## 1 Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 22.5 2.394
## max.AUCpROC.fit max.Sens.fit max.Spec.fit max.AUCROCR.fit
## 1 0.6769397 0.6335404 0.720339 0.2533951
## opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.6 0.7039376 0.654394
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.6277567 0.6561349 0.3044489
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB max.AUCROCR.OOB
## 1 0.5490597 0.4923664 0.605753 0.4400873
## opt.prob.threshold.OOB max.f.score.OOB max.Accuracy.OOB
## 1 0.95 0.6394143 0.4699552
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.440324 0.4997453 0
## max.AccuracySD.fit max.KappaSD.fit
## 1 0.009745625 0.02032591
## [1] "myfit_mdl: exit: 33.766000 secs"fit.models_0_chunk_df <-
myadd_chunk(fit.models_0_chunk_df, "fit.models_0_end", major.inc = FALSE,
label.minor = "teardown")## label step_major step_minor label_minor bgn end
## 6 fit.models_0_Low.cor.X 1 5 glmnet 158.559 192.375
## 7 fit.models_0_end 1 6 teardown 192.376 NA
## elapsed
## 6 33.816
## 7 NArm(ret_lst)
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc = FALSE)## label step_major step_minor label_minor bgn end elapsed
## 4 fit.models 4 0 0 121.782 192.389 70.607
## 5 fit.models 4 1 1 192.390 NA NAfit.models_1_chunk_df <- myadd_chunk(NULL, "fit.models_1_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_1_bgn 1 0 setup 196.828 NA NA# refactor code for outliers / ensure all model runs exclude outliers in this chunk ???
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
topindep_var <- NULL; interact_vars <- NULL;
for (mdl_id_pfx in names(glbMdlFamilies)) {
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, paste0("fit.models_1_", mdl_id_pfx),
major.inc = FALSE, label.minor = "setup")
indepVar <- NULL;
if (grepl("\\.Interact", mdl_id_pfx)) {
if (is.null(topindep_var) && is.null(interact_vars)) {
# select best glmnet model upto now
dsp_models_df <- orderBy(model_sel_frmla <- get_model_sel_frmla(),
glb_models_df)
dsp_models_df <- subset(dsp_models_df,
grepl(".glmnet", id, fixed = TRUE))
bst_mdl_id <- dsp_models_df$id[1]
mdl_id_pfx <-
paste(c(head(unlist(strsplit(bst_mdl_id, "[.]")), -1), "Interact"),
collapse=".")
# select important features
if (is.null(bst_featsimp_df <-
myget_feats_importance(glb_models_lst[[bst_mdl_id]]))) {
warning("Base model for RFE.Interact: ", bst_mdl_id,
" has no important features")
next
}
topindep_ix <- 1
while (is.null(topindep_var) && (topindep_ix <= nrow(bst_featsimp_df))) {
topindep_var <- row.names(bst_featsimp_df)[topindep_ix]
if (grepl(".fctr", topindep_var, fixed=TRUE))
topindep_var <-
paste0(unlist(strsplit(topindep_var, ".fctr"))[1], ".fctr")
if (topindep_var %in% names(glbFeatsInteractionOnly)) {
topindep_var <- NULL; topindep_ix <- topindep_ix + 1
} else break
}
# select features with importance > max(10, importance of .rnorm) & is not highest
# combine factor dummy features to just the factor feature
if (length(pos_rnorm <-
grep(".rnorm", row.names(bst_featsimp_df), fixed=TRUE)) > 0)
imp_rnorm <- bst_featsimp_df[pos_rnorm, 1] else
imp_rnorm <- NA
imp_cutoff <- max(10, imp_rnorm, na.rm=TRUE)
interact_vars <-
tail(row.names(subset(bst_featsimp_df,
imp > imp_cutoff)), -1)
if (length(interact_vars) > 0) {
interact_vars <-
myadjustInteractionFeats(glb_feats_df, myextract_actual_feats(interact_vars))
interact_vars <-
interact_vars[!grepl(topindep_var, interact_vars, fixed=TRUE)]
}
### bid0_sp only
# interact_vars <- c(
# "biddable", "D.ratio.sum.TfIdf.wrds.n", "D.TfIdf.sum.stem.stop.Ratio", "D.sum.TfIdf",
# "D.TfIdf.sum.post.stop", "D.TfIdf.sum.post.stem", "D.ratio.wrds.stop.n.wrds.n", "D.chrs.uppr.n.log",
# "D.chrs.n.log", "color.fctr"
# # , "condition.fctr", "prdl.my.descr.fctr"
# )
# interact_vars <- setdiff(interact_vars, c("startprice.dgt2.is9", "color.fctr"))
###
indepVar <- myextract_actual_feats(row.names(bst_featsimp_df))
indepVar <- setdiff(indepVar, topindep_var)
if (length(interact_vars) > 0) {
indepVar <-
setdiff(indepVar, myextract_actual_feats(interact_vars))
indepVar <- c(indepVar,
paste(topindep_var, setdiff(interact_vars, topindep_var),
sep = "*"))
} else indepVar <- union(indepVar, topindep_var)
}
}
if (is.null(indepVar))
indepVar <- glb_mdl_feats_lst[[mdl_id_pfx]]
if (is.null(indepVar) && grepl("RFE\\.", mdl_id_pfx))
indepVar <- myextract_actual_feats(predictors(rfe_fit_results))
if (is.null(indepVar))
indepVar <- mygetIndepVar(glb_feats_df)
if ((length(indepVar) == 1) && (grepl("^%<d-%", indepVar))) {
indepVar <-
eval(parse(text = str_trim(unlist(strsplit(indepVar, "%<d-%"))[2])))
}
indepVar <- myadjustInteractionFeats(glb_feats_df, indepVar)
if (grepl("\\.Interact", mdl_id_pfx)) {
# if (method != tail(unlist(strsplit(bst_mdl_id, "[.]")), 1)) next
if (is.null(glbMdlFamilies[[mdl_id_pfx]])) {
if (!is.null(glbMdlFamilies[["Best.Interact"]]))
glbMdlFamilies[[mdl_id_pfx]] <-
glbMdlFamilies[["Best.Interact"]]
}
}
if (!is.null(glbObsFitOutliers[[mdl_id_pfx]])) {
fitobs_df <- glbObsFit[!(glbObsFit[, glbFeatsId] %in%
glbObsFitOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsFit) - nrow(fitobs_df)))
print(setdiff(glbObsFit[, glbFeatsId], fitobs_df[, glbFeatsId]))
} else fitobs_df <- glbObsFit
if (is.null(glbMdlFamilies[[mdl_id_pfx]]))
mdl_methods <- glbMdlMethods else
mdl_methods <- glbMdlFamilies[[mdl_id_pfx]]
for (method in mdl_methods) {
if (method %in% c("rpart", "rf")) {
# rpart: fubar's the tree
# rf: skip the scenario w/ .rnorm for speed
indepVar <- setdiff(indepVar, c(".rnorm"))
#mdl_id <- paste0(mdl_id_pfx, ".no.rnorm")
}
fit.models_1_chunk_df <- myadd_chunk(fit.models_1_chunk_df,
paste0("fit.models_1_", mdl_id_pfx), major.inc = FALSE,
label.minor = method)
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdl_id_pfx,
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv", # or "none" if nominalWorkflow is crashing
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = fitobs_df, OOB_df = glbObsOOB)
# ntv_mdl <- glmnet(x = as.matrix(
# fitobs_df[, indepVar]),
# y = as.factor(as.character(
# fitobs_df[, glb_rsp_var])),
# family = "multinomial")
# bgn = 1; end = 100;
# ntv_mdl <- glmnet(x = as.matrix(
# subset(fitobs_df, pop.fctr != "crypto")[bgn:end, indepVar]),
# y = as.factor(as.character(
# subset(fitobs_df, pop.fctr != "crypto")[bgn:end, glb_rsp_var])),
# family = "multinomial")
}
}## label step_major step_minor label_minor bgn end
## 1 fit.models_1_bgn 1 0 setup 196.828 196.84
## 2 fit.models_1_All.X 1 1 setup 196.840 NA
## elapsed
## 1 0.012
## 2 NA
## label step_major step_minor label_minor bgn end
## 2 fit.models_1_All.X 1 1 setup 196.840 196.85
## 3 fit.models_1_All.X 1 2 glmnet 196.851 NA
## elapsed
## 2 0.01
## 3 NA
## [1] "myfit_mdl: enter: 0.001000 secs"
## [1] "fitting model: All.X##rcv#glmnet"
## [1] " indepVar: Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr"
## [1] "myfit_mdl: setup complete: 0.836000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.1, lambda = 0.0652 on full training set
## [1] "myfit_mdl: train complete: 23.709000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = mdl_id_pfx, : model's bestTune found at an extreme of
## tuneGrid for parameter: alpha## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = mdl_id_pfx, : model's bestTune found at an extreme of
## tuneGrid for parameter: lambda
## Length Class Mode
## a0 91 -none- numeric
## beta 21112 dgCMatrix S4
## df 91 -none- numeric
## dim 2 -none- numeric
## lambda 91 -none- numeric
## dev.ratio 91 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 232 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) .rnorm Edn.fctr.L
## 0.2182238650 -0.0043218147 0.0889974083
## Edn.fctr^6 Edn.fctr^7 Gender.fctrF
## 0.0094799038 0.0048448375 0.0172572894
## Gender.fctrM Hhold.fctrMKy Hhold.fctrPKn
## -0.0954525253 -0.0787132143 0.4769245380
## Hhold.fctrSKy Income.fctr.Q Income.fctr.C
## 0.0943955021 -0.1221098223 -0.0659690797
## Q100689.fctrYes Q101163.fctrDad Q101163.fctrMom
## 0.0937319604 -0.1215446266 0.0660995478
## Q101596.fctrYes Q102089.fctrRent Q102687.fctrYes
## -0.0123450142 0.0406874879 0.0264877074
## Q104996.fctrNo Q104996.fctrYes Q105655.fctrYes
## -0.0337954466 0.0101901384 -0.0114351855
## Q105840.fctrNo Q105840.fctrYes Q106042.fctrNo
## -0.0123695990 0.0344623775 -0.0630096832
## Q106388.fctrYes Q106389.fctrNo Q106997.fctrGr
## -0.0188230968 -0.0340393517 -0.0364878723
## Q107869.fctrNo Q108342.fctrOnline Q108754.fctrYes
## 0.0044655353 0.0509099257 -0.0376620607
## Q108855.fctrYes! Q108856.fctrSocialize Q109244.fctrNo
## -0.0210268035 -0.0245883944 -0.4487227152
## Q109244.fctrYes Q109367.fctrYes Q110740.fctrPC
## 0.9786872953 0.0173930011 -0.0794727701
## Q111220.fctrNo Q111220.fctrYes Q111848.fctrYes
## -0.0033922528 0.0585611159 0.0457539270
## Q112478.fctrNo Q113181.fctrNo Q113181.fctrYes
## -0.0246349466 0.1112819023 -0.1476035076
## Q113583.fctrTunes Q113992.fctrYes Q114517.fctrNo
## 0.0154543164 0.0051559413 0.0291348877
## Q115195.fctrNo Q115195.fctrYes Q115390.fctrYes
## -0.0078804951 0.0287640101 0.0480452601
## Q115610.fctrNo Q115611.fctrNo Q115611.fctrYes
## -0.0222477010 0.1250266333 -0.2789081127
## Q115899.fctrCs Q115899.fctrMe Q116197.fctrA.M.
## 0.0716304093 -0.0260904021 -0.0174322339
## Q116881.fctrHappy Q116881.fctrRight Q116953.fctrNo
## 0.0169108547 -0.1579213060 -0.0631621922
## Q118117.fctrYes Q118232.fctrId Q118233.fctrNo
## -0.0334356195 0.1000892607 -0.0512886740
## Q118892.fctrNo Q119851.fctrNo Q119851.fctrYes
## -0.0085291598 -0.0732053282 0.0864474832
## Q120012.fctrYes Q120014.fctrNo Q120014.fctrYes
## 0.0271682299 0.0120135238 -0.0072627910
## Q120194.fctrStudy first Q120379.fctrNo Q120379.fctrYes
## 0.0016623595 -0.0288424701 0.0752754524
## Q120472.fctrScience Q120650.fctrNo Q121011.fctrNo
## -0.0747816069 0.0068796862 -0.0032091223
## Q121011.fctrYes Q121699.fctrYes Q122120.fctrYes
## 0.0005825808 0.0566692057 -0.0723720439
## Q122771.fctrPt Q124122.fctrNo Q124742.fctrNo
## -0.0931571736 -0.0136270820 0.0359290161
## Q96024.fctrNo Q98059.fctrOnly-child Q98059.fctrYes
## 0.0025316228 -0.0291527328 0.0386035110
## Q98197.fctrNo Q98197.fctrYes Q98869.fctrNo
## 0.1597329673 -0.1087430705 0.2515168378
## Q99480.fctrNo Q99480.fctrYes Q99716.fctrYes
## 0.1232352423 -0.0539966633 0.0532365742
## YOB.Age.fctr.L YOB.Age.fctr.C YOB.Age.fctr^4
## 0.1045001488 -0.0057348189 0.0094887582
## YOB.Age.fctr^7 YOB.Age.fctr^8
## -0.0613013716 -0.1099161376
## [1] "max lambda < lambdaOpt:"
## (Intercept) .rnorm Edn.fctr.L
## 0.221417216 -0.006597013 0.090650240
## Edn.fctr^4 Edn.fctr^6 Edn.fctr^7
## -0.006212844 0.014671948 0.012263535
## Gender.fctrF Gender.fctrM Hhold.fctrMKy
## 0.011870040 -0.097301759 -0.085045637
## Hhold.fctrPKn Hhold.fctrSKy Income.fctr.Q
## 0.494037561 0.105977265 -0.128755036
## Income.fctr.C Q100689.fctrYes Q101162.fctrPessimist
## -0.075857022 0.101220202 -0.002204401
## Q101163.fctrDad Q101163.fctrMom Q101596.fctrYes
## -0.126578407 0.067730099 -0.016968414
## Q102089.fctrRent Q102687.fctrYes Q102906.fctrYes
## 0.043669337 0.032907509 -0.007762629
## Q104996.fctrNo Q104996.fctrYes Q105655.fctrYes
## -0.037493190 0.015130905 -0.016975835
## Q105840.fctrNo Q105840.fctrYes Q106042.fctrNo
## -0.010171139 0.036925726 -0.066503426
## Q106388.fctrYes Q106389.fctrNo Q106997.fctrGr
## -0.022943776 -0.040627101 -0.043079556
## Q107869.fctrNo Q108342.fctrOnline Q108754.fctrYes
## 0.010479401 0.056696098 -0.044397972
## Q108855.fctrYes! Q108856.fctrSocialize Q109244.fctrNo
## -0.025021908 -0.031459608 -0.456280408
## Q109244.fctrYes Q109367.fctrYes Q110740.fctrMac
## 1.002758973 0.019318706 0.002156371
## Q110740.fctrPC Q111220.fctrNo Q111220.fctrYes
## -0.084754385 -0.007032618 0.064044977
## Q111848.fctrYes Q112270.fctrNo Q112478.fctrNo
## 0.052138649 0.003287377 -0.029376738
## Q113181.fctrNo Q113181.fctrYes Q113583.fctrTunes
## 0.112453535 -0.151021176 0.019871028
## Q113992.fctrYes Q114517.fctrNo Q115195.fctrNo
## 0.011251605 0.035545764 -0.011439291
## Q115195.fctrYes Q115390.fctrYes Q115610.fctrNo
## 0.031093303 0.054301606 -0.029943924
## Q115611.fctrNo Q115611.fctrYes Q115899.fctrCs
## 0.125263509 -0.286364102 0.077026205
## Q115899.fctrMe Q116197.fctrA.M. Q116881.fctrHappy
## -0.028044295 -0.024382405 0.021409011
## Q116881.fctrRight Q116953.fctrNo Q118117.fctrYes
## -0.161417346 -0.070435474 -0.035874178
## Q118232.fctrId Q118233.fctrNo Q118892.fctrNo
## 0.108484869 -0.058777096 -0.010341717
## Q119851.fctrNo Q119851.fctrYes Q120012.fctrYes
## -0.076983210 0.090596907 0.032055116
## Q120014.fctrNo Q120014.fctrYes Q120194.fctrStudy first
## 0.014190240 -0.009626995 0.005272177
## Q120379.fctrNo Q120379.fctrYes Q120472.fctrScience
## -0.032254122 0.081003638 -0.079944132
## Q120650.fctrNo Q121011.fctrNo Q121011.fctrYes
## 0.016571439 -0.004007171 0.002867060
## Q121699.fctrYes Q122120.fctrYes Q122771.fctrPt
## 0.061730344 -0.080375537 -0.101563391
## Q123621.fctrYes Q124122.fctrNo Q124742.fctrNo
## -0.005710537 -0.018809312 0.044885981
## Q96024.fctrNo Q98059.fctrOnly-child Q98059.fctrYes
## 0.007267349 -0.042172589 0.046420210
## Q98197.fctrNo Q98197.fctrYes Q98869.fctrNo
## 0.163217987 -0.111310168 0.261203168
## Q99480.fctrNo Q99480.fctrYes Q99716.fctrYes
## 0.127854410 -0.060882172 0.055399976
## YOB.Age.fctr.L YOB.Age.fctr.C YOB.Age.fctr^4
## 0.115326080 -0.015897589 0.014310212
## YOB.Age.fctr^7 YOB.Age.fctr^8
## -0.072623853 -0.121236319
## [1] "myfit_mdl: train diagnostics complete: 24.473000 secs"
## Prediction
## Reference R D
## R 1895 198
## D 1396 964
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.420391e-01 3.040295e-01 6.277567e-01 6.561349e-01 5.299798e-01
## AccuracyPValue McnemarPValue
## 8.008482e-52 1.722168e-197
## Prediction
## Reference R D
## R 524 0
## D 591 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 4.699552e-01 0.000000e+00 4.403240e-01 4.997453e-01 5.300448e-01
## AccuracyPValue McnemarPValue
## 9.999739e-01 4.131000e-130
## [1] "myfit_mdl: predict complete: 35.142000 secs"
## id
## 1 All.X##rcv#glmnet
## feats
## 1 Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 22.747 2.521
## max.AUCpROC.fit max.Sens.fit max.Spec.fit max.AUCROCR.fit
## 1 0.6769397 0.6335404 0.720339 0.2533951
## opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.6 0.7039376 0.654394
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.6277567 0.6561349 0.3044489
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB max.AUCROCR.OOB
## 1 0.5490597 0.4923664 0.605753 0.4400873
## opt.prob.threshold.OOB max.f.score.OOB max.Accuracy.OOB
## 1 0.95 0.6394143 0.4699552
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.440324 0.4997453 0
## max.AccuracySD.fit max.KappaSD.fit
## 1 0.009745625 0.02032591
## [1] "myfit_mdl: exit: 35.158000 secs"
## label step_major step_minor label_minor bgn end
## 3 fit.models_1_All.X 1 2 glmnet 196.851 232.019
## 4 fit.models_1_All.X 1 3 glm 232.019 NA
## elapsed
## 3 35.168
## 4 NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: All.X##rcv#glm"
## [1] " indepVar: Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr"
## [1] "myfit_mdl: setup complete: 0.706000 secs"
## + Fold1.Rep1: parameter=none
## - Fold1.Rep1: parameter=none
## + Fold2.Rep1: parameter=none
## - Fold2.Rep1: parameter=none
## + Fold3.Rep1: parameter=none
## - Fold3.Rep1: parameter=none
## + Fold1.Rep2: parameter=none
## - Fold1.Rep2: parameter=none
## + Fold2.Rep2: parameter=none
## - Fold2.Rep2: parameter=none
## + Fold3.Rep2: parameter=none
## - Fold3.Rep2: parameter=none
## + Fold1.Rep3: parameter=none
## - Fold1.Rep3: parameter=none
## + Fold2.Rep3: parameter=none
## - Fold2.Rep3: parameter=none
## + Fold3.Rep3: parameter=none
## - Fold3.Rep3: parameter=none
## Aggregating results
## Fitting final model on full training set
## [1] "myfit_mdl: train complete: 14.464000 secs"
##
## Call:
## NULL
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.8061 -1.0017 0.3184 1.0062 2.4556
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.371206 0.259098 1.433 0.151947
## .rnorm -0.028152 0.034759 -0.810 0.417993
## Edn.fctr.L 0.109726 0.161046 0.681 0.495659
## Edn.fctr.Q 0.010323 0.150731 0.068 0.945398
## Edn.fctr.C -0.026307 0.130839 -0.201 0.840647
## `Edn.fctr^4` -0.213737 0.128455 -1.664 0.096132 .
## `Edn.fctr^5` -0.078006 0.117840 -0.662 0.507994
## `Edn.fctr^6` 0.115863 0.107428 1.079 0.280803
## `Edn.fctr^7` 0.138179 0.117334 1.178 0.238935
## Gender.fctrF -0.289277 0.241927 -1.196 0.231806
## Gender.fctrM -0.387166 0.237671 -1.629 0.103314
## Hhold.fctrMKn 0.050392 0.185725 0.271 0.786140
## Hhold.fctrMKy -0.085282 0.172351 -0.495 0.620730
## Hhold.fctrPKn 0.938771 0.266007 3.529 0.000417 ***
## Hhold.fctrPKy 0.087528 0.348788 0.251 0.801853
## Hhold.fctrSKn 0.161050 0.147011 1.095 0.273298
## Hhold.fctrSKy 0.394536 0.244525 1.613 0.106640
## Income.fctr.L -0.128950 0.110353 -1.169 0.242596
## Income.fctr.Q -0.266829 0.102031 -2.615 0.008918 **
## Income.fctr.C -0.208147 0.099288 -2.096 0.036048 *
## `Income.fctr^4` -0.007586 0.096441 -0.079 0.937305
## `Income.fctr^5` -0.041482 0.097575 -0.425 0.670745
## `Income.fctr^6` 0.045670 0.095164 0.480 0.631294
## Q100010.fctrNo 0.200638 0.222263 0.903 0.366683
## Q100010.fctrYes 0.124904 0.201632 0.619 0.535609
## Q100562.fctrNo 0.053527 0.204485 0.262 0.793501
## Q100562.fctrYes 0.080710 0.178803 0.451 0.651709
## Q100680.fctrNo -0.212844 0.199149 -1.069 0.285174
## Q100680.fctrYes -0.368960 0.193054 -1.911 0.055982 .
## Q100689.fctrNo 0.207610 0.195050 1.064 0.287150
## Q100689.fctrYes 0.439103 0.193737 2.266 0.023421 *
## Q101162.fctrOptimist 0.035492 0.185521 0.191 0.848281
## Q101162.fctrPessimist -0.021009 0.192148 -0.109 0.912934
## Q101163.fctrDad -0.198857 0.164855 -1.206 0.227720
## Q101163.fctrMom 0.110440 0.169032 0.653 0.513520
## Q101596.fctrNo -0.349311 0.165472 -2.111 0.034773 *
## Q101596.fctrYes -0.415336 0.175155 -2.371 0.017728 *
## Q102089.fctrOwn 0.097668 0.166494 0.587 0.557462
## Q102089.fctrRent 0.176737 0.177886 0.994 0.320446
## Q102289.fctrNo -0.146654 0.171654 -0.854 0.392905
## Q102289.fctrYes -0.126604 0.180960 -0.700 0.484163
## Q102674.fctrNo -0.255664 0.221520 -1.154 0.248445
## Q102674.fctrYes -0.178661 0.233158 -0.766 0.443517
## Q102687.fctrNo 0.646721 0.232770 2.778 0.005463 **
## Q102687.fctrYes 0.678498 0.230916 2.938 0.003300 **
## Q102906.fctrNo -0.144448 0.172137 -0.839 0.401386
## Q102906.fctrYes -0.299882 0.177325 -1.691 0.090809 .
## Q103293.fctrNo -0.013784 0.152906 -0.090 0.928171
## Q103293.fctrYes 0.074817 0.155253 0.482 0.629875
## Q104996.fctrNo -0.065172 0.147151 -0.443 0.657844
## Q104996.fctrYes 0.151651 0.143018 1.060 0.288979
## Q105655.fctrNo 0.017238 0.174490 0.099 0.921305
## Q105655.fctrYes -0.056153 0.170807 -0.329 0.742344
## Q105840.fctrNo 0.035208 0.175066 0.201 0.840610
## Q105840.fctrYes 0.102751 0.178246 0.576 0.564307
## Q106042.fctrNo -0.229945 0.178530 -1.288 0.197748
## Q106042.fctrYes -0.094961 0.176316 -0.539 0.590174
## Q106272.fctrNo -0.067920 0.201378 -0.337 0.735908
## Q106272.fctrYes 0.033967 0.185949 0.183 0.855056
## Q106388.fctrNo -0.034135 0.220492 -0.155 0.876968
## Q106388.fctrYes -0.118388 0.232903 -0.508 0.611232
## Q106389.fctrNo -0.169294 0.214139 -0.791 0.429189
## Q106389.fctrYes -0.009588 0.216396 -0.044 0.964659
## Q106993.fctrNo -0.225293 0.221136 -1.019 0.308298
## Q106993.fctrYes -0.186705 0.194256 -0.961 0.336487
## Q106997.fctrGr -0.038692 0.193207 -0.200 0.841275
## Q106997.fctrYy 0.136499 0.196521 0.695 0.487321
## Q107491.fctrNo 0.078807 0.183292 0.430 0.667232
## Q107491.fctrYes 0.092576 0.141987 0.652 0.514399
## Q107869.fctrNo 0.114791 0.147881 0.776 0.437606
## Q107869.fctrYes 0.007822 0.148130 0.053 0.957887
## `Q108342.fctrIn-person` 0.105099 0.181750 0.578 0.563088
## Q108342.fctrOnline 0.264676 0.193018 1.371 0.170296
## Q108343.fctrNo 0.023859 0.187760 0.127 0.898884
## Q108343.fctrYes 0.004976 0.198739 0.025 0.980026
## Q108617.fctrNo 0.054550 0.167813 0.325 0.745133
## Q108617.fctrYes -0.108918 0.208565 -0.522 0.601513
## Q108754.fctrNo -0.146277 0.185666 -0.788 0.430786
## Q108754.fctrYes -0.335049 0.195800 -1.711 0.087048 .
## Q108855.fctrUmm... -0.139339 0.215997 -0.645 0.518863
## `Q108855.fctrYes!` -0.222779 0.213682 -1.043 0.297147
## Q108856.fctrSocialize -0.066913 0.221027 -0.303 0.762091
## Q108856.fctrSpace 0.099104 0.206312 0.480 0.630970
## Q108950.fctrCautious 0.075287 0.156837 0.480 0.631201
## `Q108950.fctrRisk-friendly` 0.124344 0.168757 0.737 0.461228
## Q109244.fctrNo -0.621962 0.149346 -4.165 3.12e-05 ***
## Q109244.fctrYes 1.437208 0.179692 7.998 1.26e-15 ***
## Q109367.fctrNo 0.094661 0.155962 0.607 0.543883
## Q109367.fctrYes 0.078124 0.147677 0.529 0.596793
## Q110740.fctrMac 0.013742 0.132313 0.104 0.917283
## Q110740.fctrPC -0.199733 0.127953 -1.561 0.118527
## Q111220.fctrNo -0.103229 0.141703 -0.728 0.466314
## Q111220.fctrYes 0.131406 0.155276 0.846 0.397400
## Q111580.fctrDemanding -0.094305 0.158165 -0.596 0.551013
## Q111580.fctrSupportive -0.077931 0.147129 -0.530 0.596337
## Q111848.fctrNo 0.069389 0.154287 0.450 0.652901
## Q111848.fctrYes 0.222746 0.150205 1.483 0.138088
## Q112270.fctrNo 0.297042 0.149720 1.984 0.047258 *
## Q112270.fctrYes 0.295477 0.150606 1.962 0.049771 *
## Q112478.fctrNo -0.409084 0.177674 -2.302 0.021310 *
## Q112478.fctrYes -0.233061 0.171076 -1.362 0.173096
## Q112512.fctrNo 0.239220 0.188961 1.266 0.205521
## Q112512.fctrYes 0.144151 0.161261 0.894 0.371373
## Q113181.fctrNo 0.063491 0.139574 0.455 0.649186
## Q113181.fctrYes -0.298647 0.147422 -2.026 0.042786 *
## Q113583.fctrTalk 0.039916 0.206096 0.194 0.846428
## Q113583.fctrTunes 0.145082 0.197985 0.733 0.463685
## Q113584.fctrPeople 0.025377 0.204352 0.124 0.901172
## Q113584.fctrTechnology -0.022757 0.202685 -0.112 0.910603
## Q113992.fctrNo 0.090143 0.155429 0.580 0.561940
## Q113992.fctrYes 0.209102 0.166302 1.257 0.208621
## Q114152.fctrNo -0.221896 0.151526 -1.464 0.143084
## Q114152.fctrYes -0.162149 0.164239 -0.987 0.323509
## Q114386.fctrMysterious -0.062112 0.154884 -0.401 0.688403
## Q114386.fctrTMI -0.020243 0.158540 -0.128 0.898397
## Q114517.fctrNo 0.350286 0.171819 2.039 0.041481 *
## Q114517.fctrYes 0.212947 0.182957 1.164 0.244457
## Q114748.fctrNo -0.139329 0.180230 -0.773 0.439484
## Q114748.fctrYes -0.097681 0.178786 -0.546 0.584819
## Q114961.fctrNo 0.002696 0.168524 0.016 0.987238
## Q114961.fctrYes -0.011312 0.167351 -0.068 0.946109
## Q115195.fctrNo -0.076818 0.168152 -0.457 0.647787
## Q115195.fctrYes 0.047415 0.157095 0.302 0.762785
## Q115390.fctrNo 0.076750 0.155412 0.494 0.621414
## Q115390.fctrYes 0.204400 0.145388 1.406 0.159757
## Q115602.fctrNo 0.170873 0.198214 0.862 0.388653
## Q115602.fctrYes 0.117045 0.176646 0.663 0.507589
## Q115610.fctrNo -0.119502 0.212345 -0.563 0.573591
## Q115610.fctrYes 0.012962 0.186543 0.069 0.944604
## Q115611.fctrNo -0.053163 0.194370 -0.274 0.784456
## Q115611.fctrYes -0.608147 0.199321 -3.051 0.002280 **
## Q115777.fctrEnd -0.030666 0.167884 -0.183 0.855061
## Q115777.fctrStart -0.031544 0.164676 -0.192 0.848095
## Q115899.fctrCs 0.253406 0.165459 1.532 0.125638
## Q115899.fctrMe 0.010787 0.161871 0.067 0.946870
## Q116197.fctrA.M. -0.360168 0.161497 -2.230 0.025735 *
## Q116197.fctrP.M. -0.269144 0.149226 -1.804 0.071293 .
## Q116441.fctrNo 0.047891 0.182212 0.263 0.792681
## Q116441.fctrYes 0.010095 0.194848 0.052 0.958682
## Q116448.fctrNo 0.158322 0.173072 0.915 0.360311
## Q116448.fctrYes 0.127991 0.174271 0.734 0.462682
## Q116601.fctrNo 0.110019 0.197933 0.556 0.578322
## Q116601.fctrYes 0.034715 0.167826 0.207 0.836125
## Q116797.fctrNo -0.084731 0.167823 -0.505 0.613642
## Q116797.fctrYes -0.077722 0.173567 -0.448 0.654304
## Q116881.fctrHappy 0.119909 0.166315 0.721 0.470924
## Q116881.fctrRight -0.181846 0.181280 -1.003 0.315802
## Q116953.fctrNo -0.269377 0.177730 -1.516 0.129606
## Q116953.fctrYes -0.050612 0.166405 -0.304 0.761014
## `Q117186.fctrCool headed` 0.116269 0.165644 0.702 0.482730
## `Q117186.fctrHot headed` 0.038778 0.174229 0.223 0.823873
## `Q117193.fctrOdd hours` 0.049339 0.158745 0.311 0.755947
## `Q117193.fctrStandard hours` 0.005574 0.152328 0.037 0.970808
## Q118117.fctrNo 0.093111 0.151019 0.617 0.537533
## Q118117.fctrYes 0.036304 0.152283 0.238 0.811571
## Q118232.fctrId 0.488872 0.152726 3.201 0.001370 **
## Q118232.fctrPr 0.299577 0.151316 1.980 0.047725 *
## Q118233.fctrNo -0.256970 0.186889 -1.375 0.169136
## Q118233.fctrYes -0.075576 0.202056 -0.374 0.708377
## Q118237.fctrNo -0.320638 0.189499 -1.692 0.090639 .
## Q118237.fctrYes -0.300076 0.185473 -1.618 0.105686
## Q118892.fctrNo -0.030990 0.136251 -0.227 0.820075
## Q118892.fctrYes -0.005533 0.129196 -0.043 0.965839
## Q119334.fctrNo -0.049992 0.141094 -0.354 0.723100
## Q119334.fctrYes -0.057398 0.136919 -0.419 0.675060
## Q119650.fctrGiving -0.027289 0.146344 -0.186 0.852074
## Q119650.fctrReceiving 0.081838 0.162760 0.503 0.615095
## Q119851.fctrNo -0.123547 0.165059 -0.749 0.454157
## Q119851.fctrYes 0.122346 0.166446 0.735 0.462311
## Q120012.fctrNo 0.091373 0.169603 0.539 0.590060
## Q120012.fctrYes 0.206774 0.166493 1.242 0.214261
## Q120014.fctrNo -0.078807 0.158103 -0.498 0.618165
## Q120014.fctrYes -0.167816 0.150671 -1.114 0.265371
## `Q120194.fctrStudy first` 0.187874 0.145035 1.295 0.195191
## `Q120194.fctrTry first` 0.123237 0.149314 0.825 0.409169
## Q120379.fctrNo -0.059396 0.156868 -0.379 0.704959
## Q120379.fctrYes 0.160825 0.156335 1.029 0.303610
## Q120472.fctrArt -0.125269 0.161438 -0.776 0.437773
## Q120472.fctrScience -0.281027 0.150289 -1.870 0.061496 .
## Q120650.fctrNo 0.202966 0.202651 1.002 0.316558
## Q120650.fctrYes 0.039071 0.147015 0.266 0.790421
## Q120978.fctrNo 0.008515 0.158953 0.054 0.957276
## Q120978.fctrYes 0.067569 0.156204 0.433 0.665328
## Q121011.fctrNo -0.063710 0.160592 -0.397 0.691574
## Q121011.fctrYes -0.005450 0.157448 -0.035 0.972388
## Q121699.fctrNo 0.678076 0.247081 2.744 0.006063 **
## Q121699.fctrYes 0.764993 0.239844 3.190 0.001425 **
## Q121700.fctrNo -0.475786 0.240186 -1.981 0.047602 *
## Q121700.fctrYes -0.414501 0.261410 -1.586 0.112822
## Q122120.fctrNo -0.091037 0.139596 -0.652 0.514307
## Q122120.fctrYes -0.267805 0.155673 -1.720 0.085376 .
## Q122769.fctrNo 0.048175 0.215357 0.224 0.822992
## Q122769.fctrYes -0.002505 0.218140 -0.011 0.990839
## Q122770.fctrNo 0.285981 0.264798 1.080 0.280143
## Q122770.fctrYes 0.291563 0.261512 1.115 0.264888
## Q122771.fctrPc -0.368909 0.239954 -1.537 0.124191
## Q122771.fctrPt -0.576865 0.253660 -2.274 0.022956 *
## Q123464.fctrNo -0.051022 0.162812 -0.313 0.753993
## Q123464.fctrYes 0.004373 0.238104 0.018 0.985348
## Q123621.fctrNo -0.062437 0.168089 -0.371 0.710299
## Q123621.fctrYes -0.133229 0.171665 -0.776 0.437690
## Q124122.fctrNo -0.058644 0.137835 -0.425 0.670498
## Q124122.fctrYes 0.081280 0.132196 0.615 0.538657
## Q124742.fctrNo 0.174440 0.108325 1.610 0.107322
## Q124742.fctrYes -0.016295 0.125027 -0.130 0.896306
## Q96024.fctrNo 0.145614 0.133667 1.089 0.275985
## Q96024.fctrYes 0.080965 0.126986 0.638 0.523743
## `Q98059.fctrOnly-child` -0.269088 0.259995 -1.035 0.300681
## Q98059.fctrYes 0.090928 0.215316 0.422 0.672807
## Q98078.fctrNo 0.311756 0.198344 1.572 0.115998
## Q98078.fctrYes 0.173222 0.200724 0.863 0.388144
## Q98197.fctrNo 0.236567 0.190861 1.239 0.215170
## Q98197.fctrYes -0.102779 0.198491 -0.518 0.604597
## Q98578.fctrNo -0.396276 0.157266 -2.520 0.011743 *
## Q98578.fctrYes -0.405967 0.164804 -2.463 0.013765 *
## Q98869.fctrNo 0.541683 0.175372 3.089 0.002010 **
## Q98869.fctrYes 0.140725 0.148076 0.950 0.341931
## Q99480.fctrNo 0.201205 0.208583 0.965 0.334730
## Q99480.fctrYes -0.202971 0.190645 -1.065 0.287033
## Q99581.fctrNo -0.385192 0.208720 -1.846 0.064965 .
## Q99581.fctrYes -0.391573 0.236705 -1.654 0.098074 .
## Q99716.fctrNo 0.430678 0.180171 2.390 0.016831 *
## Q99716.fctrYes 0.431886 0.232818 1.855 0.063591 .
## `Q99982.fctrCheck!` -0.040738 0.196455 -0.207 0.835725
## Q99982.fctrNope 0.021110 0.199247 0.106 0.915622
## YOB.Age.fctr.L 0.382868 0.191002 2.005 0.045013 *
## YOB.Age.fctr.Q 0.196892 0.158886 1.239 0.215270
## YOB.Age.fctr.C -0.154869 0.138054 -1.122 0.261947
## `YOB.Age.fctr^4` 0.113070 0.129883 0.871 0.383999
## `YOB.Age.fctr^5` 0.062691 0.121501 0.516 0.605876
## `YOB.Age.fctr^6` 0.076196 0.108158 0.704 0.481126
## `YOB.Age.fctr^7` -0.278543 0.103874 -2.682 0.007329 **
## `YOB.Age.fctr^8` -0.343411 0.107019 -3.209 0.001332 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 6157.1 on 4452 degrees of freedom
## Residual deviance: 5103.5 on 4220 degrees of freedom
## AIC: 5569.5
##
## Number of Fisher Scoring iterations: 4
##
## [1] "myfit_mdl: train diagnostics complete: 16.594000 secs"
## Prediction
## Reference R D
## R 1861 232
## D 1296 1064
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.568605e-01 3.304977e-01 6.427047e-01 6.708104e-01 5.299798e-01
## AccuracyPValue McnemarPValue
## 4.261076e-66 7.667451e-163
## Prediction
## Reference R D
## R 513 11
## D 566 25
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 4.825112e-01 2.010196e-02 4.528118e-01 5.123031e-01 5.300448e-01
## AccuracyPValue McnemarPValue
## 9.993290e-01 1.081279e-117
## [1] "myfit_mdl: predict complete: 27.341000 secs"
## id
## 1 All.X##rcv#glm
## feats
## 1 Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 1 13.647 1.313
## max.AUCpROC.fit max.Sens.fit max.Spec.fit max.AUCROCR.fit
## 1 0.6915835 0.6789298 0.7042373 0.2344795
## opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.65 0.7089524 0.6290918
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.6427047 0.6708104 0.2564432
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB max.AUCROCR.OOB
## 1 0.5336537 0.519084 0.5482234 0.4526227
## opt.prob.threshold.OOB max.f.score.OOB max.Accuracy.OOB
## 1 0.95 0.6400499 0.4825112
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.4528118 0.5123031 0.02010196
## max.AccuracySD.fit max.KappaSD.fit
## 1 0.009053025 0.01846076
## [1] "myfit_mdl: exit: 27.355000 secs"# Check if other preProcess methods improve model performance
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, "fit.models_1_preProc", major.inc = FALSE,
label.minor = "preProc")## label step_major step_minor label_minor bgn end
## 4 fit.models_1_All.X 1 3 glm 232.019 259.424
## 5 fit.models_1_preProc 1 4 preProc 259.425 NA
## elapsed
## 4 27.406
## 5 NArequire(gdata)## Loading required package: gdata## gdata: read.xls support for 'XLS' (Excel 97-2004) files ENABLED.## ## gdata: read.xls support for 'XLSX' (Excel 2007+) files ENABLED.##
## Attaching package: 'gdata'## The following objects are masked from 'package:dplyr':
##
## combine, first, last## The following object is masked from 'package:stats':
##
## nobs## The following object is masked from 'package:utils':
##
## object.sizemdl_id <- orderBy(get_model_sel_frmla(), glb_models_df)[1, "id"]
indepVar <- trim(unlist(strsplit(glb_models_df[glb_models_df$id == mdl_id,
"feats"], "[,]")))
method <- tail(unlist(strsplit(mdl_id, "[.]")), 1)
mdl_id_pfx <- paste0(head(unlist(strsplit(mdl_id, "[.]")), -1), collapse = ".")
if (!is.null(glbObsFitOutliers[[mdl_id_pfx]])) {
fitobs_df <- glbObsFit[!(glbObsFit[, glbFeatsId] %in%
glbObsFitOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsFit) - nrow(fitobs_df)))
print(setdiff(glbObsFit[, glbFeatsId], fitobs_df[, glbFeatsId]))
} else fitobs_df <- glbObsFit
for (prePr in glb_preproc_methods) {
# The operations are applied in this order:
# Box-Cox/Yeo-Johnson transformation, centering, scaling, range, imputation, PCA, ICA then spatial sign.
ret_lst <- myfit_mdl(mdl_specs_lst=myinit_mdl_specs_lst(mdl_specs_lst=list(
id.prefix=mdl_id_pfx,
type=glb_model_type, tune.df=glbMdlTuneParams,
trainControl.method="repeatedcv",
trainControl.number=glb_rcv_n_folds,
trainControl.repeats=glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method=method, train.preProcess=prePr)),
indepVar=indepVar, rsp_var=glb_rsp_var,
fit_df=fitobs_df, OOB_df=glbObsOOB)
}
# If (All|RFE).X.glm is less accurate than Low.Cor.X.glm
# check NA coefficients & filter appropriate terms in indepVar
# if (method == "glm") {
# orig_glm <- glb_models_lst[[paste0(mdl_id, ".", model_method)]]$finalModel
# orig_glm <- glb_models_lst[["All.X.glm"]]$finalModel; print(summary(orig_glm))
# orig_glm <- glb_models_lst[["RFE.X.glm"]]$finalModel; print(summary(orig_glm))
# require(car)
# vif_orig_glm <- vif(orig_glm); print(vif_orig_glm)
# # if vif errors out with "there are aliased coefficients in the model"
# alias_orig_glm <- alias(orig_glm); alias_complete_orig_glm <- (alias_orig_glm$Complete > 0); alias_complete_orig_glm <- alias_complete_orig_glm[rowSums(alias_complete_orig_glm) > 0, colSums(alias_complete_orig_glm) > 0]; print(alias_complete_orig_glm)
# print(vif_orig_glm[!is.na(vif_orig_glm) & (vif_orig_glm == Inf)])
# print(which.max(vif_orig_glm))
# print(sort(vif_orig_glm[vif_orig_glm >= 1.0e+03], decreasing=TRUE))
# glbObsFit[c(1143, 3637, 3953, 4105), c("UniqueID", "Popular", "H.P.quandary", "Headline")]
# glb_feats_df[glb_feats_df$id %in% grep("[HSA]\\.chrs.n.log", glb_feats_df$id, value=TRUE) | glb_feats_df$cor.high.X %in% grep("[HSA]\\.chrs.n.log", glb_feats_df$id, value=TRUE), ]
# all.equal(glbObsAll$S.chrs.uppr.n.log, glbObsAll$A.chrs.uppr.n.log)
# cor(glbObsAll$S.T.herald, glbObsAll$S.T.tribun)
# mydspObs(Abstract.contains="[Dd]iar", cols=("Abstract"), all=TRUE)
# subset(glb_feats_df, cor.y.abs <= glb_feats_df[glb_feats_df$id == ".rnorm", "cor.y.abs"])
# corxx_mtrx <- cor(data.matrix(glbObsAll[, setdiff(names(glbObsAll), myfind_chr_cols_df(glbObsAll))]), use="pairwise.complete.obs"); abs_corxx_mtrx <- abs(corxx_mtrx); diag(abs_corxx_mtrx) <- 0
# which.max(abs_corxx_mtrx["S.T.tribun", ])
# abs_corxx_mtrx["A.npnct08.log", "S.npnct08.log"]
# step_glm <- step(orig_glm)
# }
# Since caret does not optimize rpart well
# if (method == "rpart")
# ret_lst <- myfit_mdl(mdl_id=paste0(mdl_id_pfx, ".cp.0"), model_method=method,
# indepVar=indepVar,
# model_type=glb_model_type,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=0, tune_models_df=data.frame(parameter="cp", min=0.0, max=0.0, by=0.1))
# User specified
# Ensure at least 2 vars in each regression; else varImp crashes
# sav_models_lst <- glb_models_lst; sav_models_df <- glb_models_df; sav_featsimp_df <- glb_featsimp_df; all.equal(sav_featsimp_df, glb_featsimp_df)
# glb_models_lst <- sav_models_lst; glb_models_df <- sav_models_df; glm_featsimp_df <- sav_featsimp_df
# easier to exclude features
# require(gdata) # needed for trim
# mdl_id <- "";
# indepVar <- head(subset(glb_models_df, grepl("All\\.X\\.", mdl_id), select=feats)
# , 1)[, "feats"]
# indepVar <- trim(unlist(strsplit(indepVar, "[,]")))
# indepVar <- setdiff(indepVar, ".rnorm")
# easier to include features
#stop(here"); sav_models_df <- glb_models_df; glb_models_df <- sav_models_df
# !_sp
# mdl_id <- "csm"; indepVar <- c(NULL
# ,"prdline.my.fctr", "prdline.my.fctr:.clusterid.fctr"
# ,"prdline.my.fctr*biddable"
# #,"prdline.my.fctr*startprice.log"
# #,"prdline.my.fctr*startprice.diff"
# ,"prdline.my.fctr*condition.fctr"
# ,"prdline.my.fctr*D.terms.post.stop.n"
# #,"prdline.my.fctr*D.terms.post.stem.n"
# ,"prdline.my.fctr*cellular.fctr"
# # ,"<feat1>:<feat2>"
# )
# for (method in glbMdlMethods) {
# ret_lst <- myfit_mdl(mdl_id=mdl_id, model_method=method,
# indepVar=indepVar,
# model_type=glb_model_type,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=glb_rcv_n_folds, tune_models_df=glbMdlTuneParams)
# csm_mdl_id <- paste0(mdl_id, ".", method)
# csm_featsimp_df <- myget_feats_importance(glb_models_lst[[paste0(mdl_id, ".",
# method)]]); print(head(csm_featsimp_df))
# }
###
# Ntv.1.lm <- lm(reformulate(indepVar, glb_rsp_var), glbObsTrn); print(summary(Ntv.1.lm))
#glb_models_df[, "max.Accuracy.OOB", FALSE]
#varImp(glb_models_lst[["Low.cor.X.glm"]])
#orderBy(~ -Overall, varImp(glb_models_lst[["All.X.2.glm"]])$imp)
#orderBy(~ -Overall, varImp(glb_models_lst[["All.X.3.glm"]])$imp)
#glb_feats_df[grepl("npnct28", glb_feats_df$id), ]
# User specified bivariate models
# indepVar_lst <- list()
# for (feat in setdiff(names(glbObsFit),
# union(glb_rsp_var, glbFeatsExclude)))
# indepVar_lst[["feat"]] <- feat
# User specified combinatorial models
# indepVar_lst <- list()
# combn_mtrx <- combn(c("<feat1_name>", "<feat2_name>", "<featn_name>"),
# <num_feats_to_choose>)
# for (combn_ix in 1:ncol(combn_mtrx))
# #print(combn_mtrx[, combn_ix])
# indepVar_lst[[combn_ix]] <- combn_mtrx[, combn_ix]
# template for myfit_mdl
# rf is hard-coded in caret to recognize only Accuracy / Kappa evaluation metrics
# only for OOB in trainControl ?
# ret_lst <- myfit_mdl_fn(mdl_id=paste0(mdl_id_pfx, ""), model_method=method,
# indepVar=indepVar,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=glb_rcv_n_folds, tune_models_df=glbMdlTuneParams,
# model_loss_mtrx=glbMdlMetric_terms,
# model_summaryFunction=glbMdlMetricSummaryFn,
# model_metric=glbMdlMetricSummary,
# model_metric_maximize=glbMdlMetricMaximize)
# Simplify a model
# fit_df <- glbObsFit; glb_mdl <- step(<complex>_mdl)
# Non-caret models
# rpart_area_mdl <- rpart(reformulate("Area", response=glb_rsp_var),
# data=glbObsFit, #method="class",
# control=rpart.control(cp=0.12),
# parms=list(loss=glbMdlMetric_terms))
# print("rpart_sel_wlm_mdl"); prp(rpart_sel_wlm_mdl)
#
print(glb_models_df)## id
## MFO###myMFO_classfr MFO###myMFO_classfr
## Random###myrandom_classfr Random###myrandom_classfr
## Max.cor.Y.rcv.1X1###glmnet Max.cor.Y.rcv.1X1###glmnet
## Max.cor.Y##rcv#rpart Max.cor.Y##rcv#rpart
## Interact.High.cor.Y##rcv#glmnet Interact.High.cor.Y##rcv#glmnet
## Low.cor.X##rcv#glmnet Low.cor.X##rcv#glmnet
## All.X##rcv#glmnet All.X##rcv#glmnet
## All.X##rcv#glm All.X##rcv#glm
## feats
## MFO###myMFO_classfr .rnorm
## Random###myrandom_classfr .rnorm
## Max.cor.Y.rcv.1X1###glmnet Q109244.fctr,Gender.fctr
## Max.cor.Y##rcv#rpart Q109244.fctr,Gender.fctr
## Interact.High.cor.Y##rcv#glmnet Q109244.fctr,Gender.fctr,Q109244.fctr:Q99480.fctr,Q109244.fctr:Q98078.fctr,Q109244.fctr:Q100689.fctr,Q109244.fctr:Q108855.fctr,Q109244.fctr:Q123621.fctr,Q109244.fctr:Q122771.fctr,Q109244.fctr:Q120472.fctr,Q109244.fctr:Q106272.fctr
## Low.cor.X##rcv#glmnet Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## All.X##rcv#glmnet Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## All.X##rcv#glm Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## max.nTuningRuns min.elapsedtime.everything
## MFO###myMFO_classfr 0 0.362
## Random###myrandom_classfr 0 0.273
## Max.cor.Y.rcv.1X1###glmnet 0 0.725
## Max.cor.Y##rcv#rpart 5 1.522
## Interact.High.cor.Y##rcv#glmnet 25 5.320
## Low.cor.X##rcv#glmnet 25 22.500
## All.X##rcv#glmnet 25 22.747
## All.X##rcv#glm 1 13.647
## min.elapsedtime.final max.AUCpROC.fit
## MFO###myMFO_classfr 0.004 0.5000000
## Random###myrandom_classfr 0.002 0.4943556
## Max.cor.Y.rcv.1X1###glmnet 0.063 0.6195812
## Max.cor.Y##rcv#rpart 0.018 0.6195812
## Interact.High.cor.Y##rcv#glmnet 0.330 0.6372713
## Low.cor.X##rcv#glmnet 2.394 0.6769397
## All.X##rcv#glmnet 2.521 0.6769397
## All.X##rcv#glm 1.313 0.6915835
## max.Sens.fit max.Spec.fit max.AUCROCR.fit
## MFO###myMFO_classfr 0.0000000 1.0000000 0.5000000
## Random###myrandom_classfr 0.4620162 0.5266949 0.4989014
## Max.cor.Y.rcv.1X1###glmnet 0.5671285 0.6720339 0.3267482
## Max.cor.Y##rcv#rpart 0.5671285 0.6720339 0.3369762
## Interact.High.cor.Y##rcv#glmnet 0.6364071 0.6381356 0.3046595
## Low.cor.X##rcv#glmnet 0.6335404 0.7203390 0.2533951
## All.X##rcv#glmnet 0.6335404 0.7203390 0.2533951
## All.X##rcv#glm 0.6789298 0.7042373 0.2344795
## opt.prob.threshold.fit max.f.score.fit
## MFO###myMFO_classfr 0.50 0.6394745
## Random###myrandom_classfr 0.55 0.6394745
## Max.cor.Y.rcv.1X1###glmnet 0.60 0.6875862
## Max.cor.Y##rcv#rpart 0.55 0.6875862
## Interact.High.cor.Y##rcv#glmnet 0.65 0.6891490
## Low.cor.X##rcv#glmnet 0.60 0.7039376
## All.X##rcv#glmnet 0.60 0.7039376
## All.X##rcv#glm 0.65 0.7089524
## max.Accuracy.fit max.AccuracyLower.fit
## MFO###myMFO_classfr 0.4700202 0.4552725
## Random###myrandom_classfr 0.4700202 0.4552725
## Max.cor.Y.rcv.1X1###glmnet 0.5930833 0.5784850
## Max.cor.Y##rcv#rpart 0.6227314 0.5784850
## Interact.High.cor.Y##rcv#glmnet 0.6276719 0.5859338
## Low.cor.X##rcv#glmnet 0.6543940 0.6277567
## All.X##rcv#glmnet 0.6543940 0.6277567
## All.X##rcv#glm 0.6290918 0.6427047
## max.AccuracyUpper.fit max.Kappa.fit
## MFO###myMFO_classfr 0.4848073 0.0000000
## Random###myrandom_classfr 0.4848073 0.0000000
## Max.cor.Y.rcv.1X1###glmnet 0.6075594 0.2173699
## Max.cor.Y##rcv#rpart 0.6075594 0.2400193
## Interact.High.cor.Y##rcv#glmnet 0.6149224 0.2550614
## Low.cor.X##rcv#glmnet 0.6561349 0.3044489
## All.X##rcv#glmnet 0.6561349 0.3044489
## All.X##rcv#glm 0.6708104 0.2564432
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB
## MFO###myMFO_classfr 0.5000000 0.0000000 1.0000000
## Random###myrandom_classfr 0.5268661 0.5038168 0.5499154
## Max.cor.Y.rcv.1X1###glmnet 0.4999322 0.4465649 0.5532995
## Max.cor.Y##rcv#rpart 0.4999322 0.4465649 0.5532995
## Interact.High.cor.Y##rcv#glmnet 0.5157790 0.5171756 0.5143824
## Low.cor.X##rcv#glmnet 0.5490597 0.4923664 0.6057530
## All.X##rcv#glmnet 0.5490597 0.4923664 0.6057530
## All.X##rcv#glm 0.5336537 0.5190840 0.5482234
## max.AUCROCR.OOB opt.prob.threshold.OOB
## MFO###myMFO_classfr 0.5000000 0.50
## Random###myrandom_classfr 0.5178149 0.55
## Max.cor.Y.rcv.1X1###glmnet 0.4910312 0.90
## Max.cor.Y##rcv#rpart 0.4999354 0.90
## Interact.High.cor.Y##rcv#glmnet 0.4731743 1.00
## Low.cor.X##rcv#glmnet 0.4400873 0.95
## All.X##rcv#glmnet 0.4400873 0.95
## All.X##rcv#glm 0.4526227 0.95
## max.f.score.OOB max.Accuracy.OOB
## MFO###myMFO_classfr 0.6394143 0.4699552
## Random###myrandom_classfr 0.6394143 0.4699552
## Max.cor.Y.rcv.1X1###glmnet 0.6394143 0.4699552
## Max.cor.Y##rcv#rpart 0.6394143 0.4699552
## Interact.High.cor.Y##rcv#glmnet 0.6394143 0.4699552
## Low.cor.X##rcv#glmnet 0.6394143 0.4699552
## All.X##rcv#glmnet 0.6394143 0.4699552
## All.X##rcv#glm 0.6400499 0.4825112
## max.AccuracyLower.OOB
## MFO###myMFO_classfr 0.4403240
## Random###myrandom_classfr 0.4403240
## Max.cor.Y.rcv.1X1###glmnet 0.4403240
## Max.cor.Y##rcv#rpart 0.4403240
## Interact.High.cor.Y##rcv#glmnet 0.4403240
## Low.cor.X##rcv#glmnet 0.4403240
## All.X##rcv#glmnet 0.4403240
## All.X##rcv#glm 0.4528118
## max.AccuracyUpper.OOB max.Kappa.OOB
## MFO###myMFO_classfr 0.4997453 0.00000000
## Random###myrandom_classfr 0.4997453 0.00000000
## Max.cor.Y.rcv.1X1###glmnet 0.4997453 0.00000000
## Max.cor.Y##rcv#rpart 0.4997453 0.00000000
## Interact.High.cor.Y##rcv#glmnet 0.4997453 0.00000000
## Low.cor.X##rcv#glmnet 0.4997453 0.00000000
## All.X##rcv#glmnet 0.4997453 0.00000000
## All.X##rcv#glm 0.5123031 0.02010196
## max.AccuracySD.fit max.KappaSD.fit
## MFO###myMFO_classfr NA NA
## Random###myrandom_classfr NA NA
## Max.cor.Y.rcv.1X1###glmnet NA NA
## Max.cor.Y##rcv#rpart 0.014202428 0.02887036
## Interact.High.cor.Y##rcv#glmnet 0.012724205 0.02650871
## Low.cor.X##rcv#glmnet 0.009745625 0.02032591
## All.X##rcv#glmnet 0.009745625 0.02032591
## All.X##rcv#glm 0.009053025 0.01846076rm(ret_lst)
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, "fit.models_1_end", major.inc = FALSE,
label.minor = "teardown")## label step_major step_minor label_minor bgn end
## 5 fit.models_1_preProc 1 4 preProc 259.425 260.511
## 6 fit.models_1_end 1 5 teardown 260.511 NA
## elapsed
## 5 1.086
## 6 NAglb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc = FALSE)## label step_major step_minor label_minor bgn end elapsed
## 5 fit.models 4 1 1 192.390 260.52 68.131
## 6 fit.models 4 2 2 260.521 NA NAfit.models_2_chunk_df <-
myadd_chunk(NULL, "fit.models_2_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_2_bgn 1 0 setup 264.622 NA NAplt_models_df <- glb_models_df[, -grep("SD|Upper|Lower", names(glb_models_df))]
for (var in grep("^min.", names(plt_models_df), value=TRUE)) {
plt_models_df[, sub("min.", "inv.", var)] <-
#ifelse(all(is.na(tmp <- plt_models_df[, var])), NA, 1.0 / tmp)
1.0 / plt_models_df[, var]
plt_models_df <- plt_models_df[ , -grep(var, names(plt_models_df))]
}
print(plt_models_df)## id
## MFO###myMFO_classfr MFO###myMFO_classfr
## Random###myrandom_classfr Random###myrandom_classfr
## Max.cor.Y.rcv.1X1###glmnet Max.cor.Y.rcv.1X1###glmnet
## Max.cor.Y##rcv#rpart Max.cor.Y##rcv#rpart
## Interact.High.cor.Y##rcv#glmnet Interact.High.cor.Y##rcv#glmnet
## Low.cor.X##rcv#glmnet Low.cor.X##rcv#glmnet
## All.X##rcv#glmnet All.X##rcv#glmnet
## All.X##rcv#glm All.X##rcv#glm
## feats
## MFO###myMFO_classfr .rnorm
## Random###myrandom_classfr .rnorm
## Max.cor.Y.rcv.1X1###glmnet Q109244.fctr,Gender.fctr
## Max.cor.Y##rcv#rpart Q109244.fctr,Gender.fctr
## Interact.High.cor.Y##rcv#glmnet Q109244.fctr,Gender.fctr,Q109244.fctr:Q99480.fctr,Q109244.fctr:Q98078.fctr,Q109244.fctr:Q100689.fctr,Q109244.fctr:Q108855.fctr,Q109244.fctr:Q123621.fctr,Q109244.fctr:Q122771.fctr,Q109244.fctr:Q120472.fctr,Q109244.fctr:Q106272.fctr
## Low.cor.X##rcv#glmnet Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## All.X##rcv#glmnet Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## All.X##rcv#glm Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## max.nTuningRuns max.AUCpROC.fit
## MFO###myMFO_classfr 0 0.5000000
## Random###myrandom_classfr 0 0.4943556
## Max.cor.Y.rcv.1X1###glmnet 0 0.6195812
## Max.cor.Y##rcv#rpart 5 0.6195812
## Interact.High.cor.Y##rcv#glmnet 25 0.6372713
## Low.cor.X##rcv#glmnet 25 0.6769397
## All.X##rcv#glmnet 25 0.6769397
## All.X##rcv#glm 1 0.6915835
## max.Sens.fit max.Spec.fit max.AUCROCR.fit
## MFO###myMFO_classfr 0.0000000 1.0000000 0.5000000
## Random###myrandom_classfr 0.4620162 0.5266949 0.4989014
## Max.cor.Y.rcv.1X1###glmnet 0.5671285 0.6720339 0.3267482
## Max.cor.Y##rcv#rpart 0.5671285 0.6720339 0.3369762
## Interact.High.cor.Y##rcv#glmnet 0.6364071 0.6381356 0.3046595
## Low.cor.X##rcv#glmnet 0.6335404 0.7203390 0.2533951
## All.X##rcv#glmnet 0.6335404 0.7203390 0.2533951
## All.X##rcv#glm 0.6789298 0.7042373 0.2344795
## opt.prob.threshold.fit max.f.score.fit
## MFO###myMFO_classfr 0.50 0.6394745
## Random###myrandom_classfr 0.55 0.6394745
## Max.cor.Y.rcv.1X1###glmnet 0.60 0.6875862
## Max.cor.Y##rcv#rpart 0.55 0.6875862
## Interact.High.cor.Y##rcv#glmnet 0.65 0.6891490
## Low.cor.X##rcv#glmnet 0.60 0.7039376
## All.X##rcv#glmnet 0.60 0.7039376
## All.X##rcv#glm 0.65 0.7089524
## max.Accuracy.fit max.Kappa.fit
## MFO###myMFO_classfr 0.4700202 0.0000000
## Random###myrandom_classfr 0.4700202 0.0000000
## Max.cor.Y.rcv.1X1###glmnet 0.5930833 0.2173699
## Max.cor.Y##rcv#rpart 0.6227314 0.2400193
## Interact.High.cor.Y##rcv#glmnet 0.6276719 0.2550614
## Low.cor.X##rcv#glmnet 0.6543940 0.3044489
## All.X##rcv#glmnet 0.6543940 0.3044489
## All.X##rcv#glm 0.6290918 0.2564432
## max.AUCpROC.OOB max.Sens.OOB max.Spec.OOB
## MFO###myMFO_classfr 0.5000000 0.0000000 1.0000000
## Random###myrandom_classfr 0.5268661 0.5038168 0.5499154
## Max.cor.Y.rcv.1X1###glmnet 0.4999322 0.4465649 0.5532995
## Max.cor.Y##rcv#rpart 0.4999322 0.4465649 0.5532995
## Interact.High.cor.Y##rcv#glmnet 0.5157790 0.5171756 0.5143824
## Low.cor.X##rcv#glmnet 0.5490597 0.4923664 0.6057530
## All.X##rcv#glmnet 0.5490597 0.4923664 0.6057530
## All.X##rcv#glm 0.5336537 0.5190840 0.5482234
## max.AUCROCR.OOB opt.prob.threshold.OOB
## MFO###myMFO_classfr 0.5000000 0.50
## Random###myrandom_classfr 0.5178149 0.55
## Max.cor.Y.rcv.1X1###glmnet 0.4910312 0.90
## Max.cor.Y##rcv#rpart 0.4999354 0.90
## Interact.High.cor.Y##rcv#glmnet 0.4731743 1.00
## Low.cor.X##rcv#glmnet 0.4400873 0.95
## All.X##rcv#glmnet 0.4400873 0.95
## All.X##rcv#glm 0.4526227 0.95
## max.f.score.OOB max.Accuracy.OOB
## MFO###myMFO_classfr 0.6394143 0.4699552
## Random###myrandom_classfr 0.6394143 0.4699552
## Max.cor.Y.rcv.1X1###glmnet 0.6394143 0.4699552
## Max.cor.Y##rcv#rpart 0.6394143 0.4699552
## Interact.High.cor.Y##rcv#glmnet 0.6394143 0.4699552
## Low.cor.X##rcv#glmnet 0.6394143 0.4699552
## All.X##rcv#glmnet 0.6394143 0.4699552
## All.X##rcv#glm 0.6400499 0.4825112
## max.Kappa.OOB inv.elapsedtime.everything
## MFO###myMFO_classfr 0.00000000 2.76243094
## Random###myrandom_classfr 0.00000000 3.66300366
## Max.cor.Y.rcv.1X1###glmnet 0.00000000 1.37931034
## Max.cor.Y##rcv#rpart 0.00000000 0.65703022
## Interact.High.cor.Y##rcv#glmnet 0.00000000 0.18796992
## Low.cor.X##rcv#glmnet 0.00000000 0.04444444
## All.X##rcv#glmnet 0.00000000 0.04396184
## All.X##rcv#glm 0.02010196 0.07327618
## inv.elapsedtime.final
## MFO###myMFO_classfr 250.0000000
## Random###myrandom_classfr 500.0000000
## Max.cor.Y.rcv.1X1###glmnet 15.8730159
## Max.cor.Y##rcv#rpart 55.5555556
## Interact.High.cor.Y##rcv#glmnet 3.0303030
## Low.cor.X##rcv#glmnet 0.4177109
## All.X##rcv#glmnet 0.3966680
## All.X##rcv#glm 0.7616146# print(myplot_radar(radar_inp_df=plt_models_df))
# print(myplot_radar(radar_inp_df=subset(plt_models_df,
# !(mdl_id %in% grep("random|MFO", plt_models_df$id, value=TRUE)))))
# Compute CI for <metric>SD
glb_models_df <- mutate(glb_models_df,
max.df = ifelse(max.nTuningRuns > 1, max.nTuningRuns - 1, NA),
min.sd2ci.scaler = ifelse(is.na(max.df), NA, qt(0.975, max.df)))
for (var in grep("SD", names(glb_models_df), value=TRUE)) {
# Does CI alredy exist ?
var_components <- unlist(strsplit(var, "SD"))
varActul <- paste0(var_components[1], var_components[2])
varUpper <- paste0(var_components[1], "Upper", var_components[2])
varLower <- paste0(var_components[1], "Lower", var_components[2])
if (varUpper %in% names(glb_models_df)) {
warning(varUpper, " already exists in glb_models_df")
# Assuming Lower also exists
next
}
print(sprintf("var:%s", var))
# CI is dependent on sample size in t distribution; df=n-1
glb_models_df[, varUpper] <- glb_models_df[, varActul] +
glb_models_df[, "min.sd2ci.scaler"] * glb_models_df[, var]
glb_models_df[, varLower] <- glb_models_df[, varActul] -
glb_models_df[, "min.sd2ci.scaler"] * glb_models_df[, var]
}## Warning: max.AccuracyUpper.fit already exists in glb_models_df## [1] "var:max.KappaSD.fit"# Plot metrics with CI
plt_models_df <- glb_models_df[, "id", FALSE]
pltCI_models_df <- glb_models_df[, "id", FALSE]
for (var in grep("Upper", names(glb_models_df), value=TRUE)) {
var_components <- unlist(strsplit(var, "Upper"))
col_name <- unlist(paste(var_components, collapse=""))
plt_models_df[, col_name] <- glb_models_df[, col_name]
for (name in paste0(var_components[1], c("Upper", "Lower"), var_components[2]))
pltCI_models_df[, name] <- glb_models_df[, name]
}
build_statsCI_data <- function(plt_models_df) {
mltd_models_df <- melt(plt_models_df, id.vars="id")
mltd_models_df$data <- sapply(1:nrow(mltd_models_df),
function(row_ix) tail(unlist(strsplit(as.character(
mltd_models_df[row_ix, "variable"]), "[.]")), 1))
mltd_models_df$label <- sapply(1:nrow(mltd_models_df),
function(row_ix) head(unlist(strsplit(as.character(
mltd_models_df[row_ix, "variable"]),
paste0(".", mltd_models_df[row_ix, "data"]))), 1))
#print(mltd_models_df)
return(mltd_models_df)
}
mltd_models_df <- build_statsCI_data(plt_models_df)
mltdCI_models_df <- melt(pltCI_models_df, id.vars="id")
for (row_ix in 1:nrow(mltdCI_models_df)) {
for (type in c("Upper", "Lower")) {
if (length(var_components <- unlist(strsplit(
as.character(mltdCI_models_df[row_ix, "variable"]), type))) > 1) {
#print(sprintf("row_ix:%d; type:%s; ", row_ix, type))
mltdCI_models_df[row_ix, "label"] <- var_components[1]
mltdCI_models_df[row_ix, "data"] <-
unlist(strsplit(var_components[2], "[.]"))[2]
mltdCI_models_df[row_ix, "type"] <- type
break
}
}
}
wideCI_models_df <- reshape(subset(mltdCI_models_df, select=-variable),
timevar="type",
idvar=setdiff(names(mltdCI_models_df), c("type", "value", "variable")),
direction="wide")
#print(wideCI_models_df)
mrgdCI_models_df <- merge(wideCI_models_df, mltd_models_df, all.x=TRUE)
#print(mrgdCI_models_df)
# Merge stats back in if CIs don't exist
goback_vars <- c()
for (var in unique(mltd_models_df$label)) {
for (type in unique(mltd_models_df$data)) {
var_type <- paste0(var, ".", type)
# if this data is already present, next
if (var_type %in% unique(paste(mltd_models_df$label, mltd_models_df$data,
sep=".")))
next
#print(sprintf("var_type:%s", var_type))
goback_vars <- c(goback_vars, var_type)
}
}
if (length(goback_vars) > 0) {
mltd_goback_df <- build_statsCI_data(glb_models_df[, c("id", goback_vars)])
mltd_models_df <- rbind(mltd_models_df, mltd_goback_df)
}
# mltd_models_df <- merge(mltd_models_df, glb_models_df[, c("id", "model_method")],
# all.x=TRUE)
png(paste0(glbOut$pfx, "models_bar.png"), width=480*3, height=480*2)
#print(gp <- myplot_bar(mltd_models_df, "id", "value", colorcol_name="model_method") +
print(gp <- myplot_bar(df=mltd_models_df, xcol_name="id", ycol_names="value") +
geom_errorbar(data=mrgdCI_models_df,
mapping=aes(x=mdl_id, ymax=value.Upper, ymin=value.Lower), width=0.5) +
facet_grid(label ~ data, scales="free") +
theme(axis.text.x = element_text(angle = 90,vjust = 0.5)))## Warning: Removed 4 rows containing missing values (geom_errorbar).dev.off()## quartz_off_screen
## 2print(gp)## Warning: Removed 4 rows containing missing values (geom_errorbar).
dsp_models_cols <- c("id",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
# if (glb_is_classification && glb_is_binomial)
# dsp_models_cols <- c(dsp_models_cols, "opt.prob.threshold.OOB")
print(dsp_models_df <- orderBy(get_model_sel_frmla(), glb_models_df)[, dsp_models_cols])## id max.Accuracy.OOB max.AUCROCR.OOB
## 8 All.X##rcv#glm 0.4825112 0.4526227
## 2 Random###myrandom_classfr 0.4699552 0.5178149
## 1 MFO###myMFO_classfr 0.4699552 0.5000000
## 4 Max.cor.Y##rcv#rpart 0.4699552 0.4999354
## 3 Max.cor.Y.rcv.1X1###glmnet 0.4699552 0.4910312
## 5 Interact.High.cor.Y##rcv#glmnet 0.4699552 0.4731743
## 6 Low.cor.X##rcv#glmnet 0.4699552 0.4400873
## 7 All.X##rcv#glmnet 0.4699552 0.4400873
## max.AUCpROC.OOB max.Accuracy.fit opt.prob.threshold.fit
## 8 0.5336537 0.6290918 0.65
## 2 0.5268661 0.4700202 0.55
## 1 0.5000000 0.4700202 0.50
## 4 0.4999322 0.6227314 0.55
## 3 0.4999322 0.5930833 0.60
## 5 0.5157790 0.6276719 0.65
## 6 0.5490597 0.6543940 0.60
## 7 0.5490597 0.6543940 0.60
## opt.prob.threshold.OOB
## 8 0.95
## 2 0.55
## 1 0.50
## 4 0.90
## 3 0.90
## 5 1.00
## 6 0.95
## 7 0.95# print(myplot_radar(radar_inp_df = dsp_models_df))
print("Metrics used for model selection:"); print(get_model_sel_frmla())## [1] "Metrics used for model selection:"## ~-max.Accuracy.OOB - max.AUCROCR.OOB - max.AUCpROC.OOB - max.Accuracy.fit -
## opt.prob.threshold.OOB
## <environment: 0x7fedb894bb88>print(sprintf("Best model id: %s", dsp_models_df[1, "id"]))## [1] "Best model id: All.X##rcv#glm"glb_get_predictions <- function(df, mdl_id, rsp_var, prob_threshold_def=NULL, verbose=FALSE) {
mdl <- glb_models_lst[[mdl_id]]
clmnNames <- mygetPredictIds(rsp_var, mdl_id)
predct_var_name <- clmnNames$value
predct_prob_var_name <- clmnNames$prob
predct_accurate_var_name <- clmnNames$is.acc
predct_error_var_name <- clmnNames$err
predct_erabs_var_name <- clmnNames$err.abs
if (glb_is_regression) {
df[, predct_var_name] <- predict(mdl, newdata=df, type="raw")
if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_var_name) +
facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="glm"))
df[, predct_error_var_name] <- df[, predct_var_name] - df[, glb_rsp_var]
if (verbose) print(myplot_scatter(df, predct_var_name, predct_error_var_name) +
#facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="auto"))
if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_error_var_name) +
#facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="glm"))
df[, predct_erabs_var_name] <- abs(df[, predct_error_var_name])
if (verbose) print(head(orderBy(reformulate(c("-", predct_erabs_var_name)), df)))
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
if (glb_is_classification && glb_is_binomial) {
prob_threshold <- glb_models_df[glb_models_df$id == mdl_id,
"opt.prob.threshold.OOB"]
if (is.null(prob_threshold) || is.na(prob_threshold)) {
warning("Using default probability threshold: ", prob_threshold_def)
if (is.null(prob_threshold <- prob_threshold_def))
stop("Default probability threshold is NULL")
}
df[, predct_prob_var_name] <- predict(mdl, newdata = df, type = "prob")[, 2]
df[, predct_var_name] <-
factor(levels(df[, glb_rsp_var])[
(df[, predct_prob_var_name] >=
prob_threshold) * 1 + 1], levels(df[, glb_rsp_var]))
# if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_var_name) +
# facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="glm"))
df[, predct_error_var_name] <- df[, predct_var_name] != df[, glb_rsp_var]
# if (verbose) print(myplot_scatter(df, predct_var_name, predct_error_var_name) +
# #facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="auto"))
# if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_error_var_name) +
# #facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="glm"))
# if prediction is a TP (true +ve), measure distance from 1.0
tp <- which((df[, predct_var_name] == df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[2]))
df[tp, predct_erabs_var_name] <- abs(1 - df[tp, predct_prob_var_name])
#rowIx <- which.max(df[tp, predct_erabs_var_name]); df[tp, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a TN (true -ve), measure distance from 0.0
tn <- which((df[, predct_var_name] == df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[1]))
df[tn, predct_erabs_var_name] <- abs(0 - df[tn, predct_prob_var_name])
#rowIx <- which.max(df[tn, predct_erabs_var_name]); df[tn, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a FP (flse +ve), measure distance from 0.0
fp <- which((df[, predct_var_name] != df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[2]))
df[fp, predct_erabs_var_name] <- abs(0 - df[fp, predct_prob_var_name])
#rowIx <- which.max(df[fp, predct_erabs_var_name]); df[fp, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a FN (flse -ve), measure distance from 1.0
fn <- which((df[, predct_var_name] != df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[1]))
df[fn, predct_erabs_var_name] <- abs(1 - df[fn, predct_prob_var_name])
#rowIx <- which.max(df[fn, predct_erabs_var_name]); df[fn, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
if (verbose) print(head(orderBy(reformulate(c("-", predct_erabs_var_name)), df)))
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
if (glb_is_classification && !glb_is_binomial) {
df[, predct_var_name] <- predict(mdl, newdata = df, type = "raw")
probCls <- predict(mdl, newdata = df, type = "prob")
df[, predct_prob_var_name] <- NA
for (cls in names(probCls)) {
mask <- (df[, predct_var_name] == cls)
df[mask, predct_prob_var_name] <- probCls[mask, cls]
}
if (verbose) print(myplot_histogram(df, predct_prob_var_name,
fill_col_name = predct_var_name))
if (verbose) print(myplot_histogram(df, predct_prob_var_name,
facet_frmla = paste0("~", glb_rsp_var)))
df[, predct_error_var_name] <- df[, predct_var_name] != df[, glb_rsp_var]
# if prediction is erroneous, measure predicted class prob from actual class prob
df[, predct_erabs_var_name] <- 0
for (cls in names(probCls)) {
mask <- (df[, glb_rsp_var] == cls) & (df[, predct_error_var_name])
df[mask, predct_erabs_var_name] <- probCls[mask, cls]
}
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
return(df)
}
#stop(here"); glb2Sav(); glbObsAll <- savObsAll; glbObsTrn <- savObsTrn; glbObsFit <- savObsFit; glbObsOOB <- savObsOOB; sav_models_df <- glb_models_df; glb_models_df <- sav_models_df; glb_featsimp_df <- sav_featsimp_df
myget_category_stats <- function(obs_df, mdl_id, label) {
require(dplyr)
require(lazyeval)
predct_var_name <- mygetPredictIds(glb_rsp_var, mdl_id)$value
predct_error_var_name <- mygetPredictIds(glb_rsp_var, mdl_id)$err.abs
if (!predct_var_name %in% names(obs_df))
obs_df <- glb_get_predictions(obs_df, mdl_id, glb_rsp_var)
tmp_obs_df <- obs_df[, c(glbFeatsCategory, glb_rsp_var,
predct_var_name, predct_error_var_name)]
# tmp_obs_df <- obs_df %>%
# dplyr::select_(glbFeatsCategory, glb_rsp_var, predct_var_name, predct_error_var_name)
#dplyr::rename(startprice.log10.predict.RFE.X.glmnet.err=error_abs_OOB)
names(tmp_obs_df)[length(names(tmp_obs_df))] <- paste0("err.abs.", label)
ret_ctgry_df <- tmp_obs_df %>%
dplyr::group_by_(glbFeatsCategory) %>%
dplyr::summarise_(#interp(~sum(abs(var)), var=as.name(glb_rsp_var)),
interp(~sum(var), var=as.name(paste0("err.abs.", label))),
interp(~mean(var), var=as.name(paste0("err.abs.", label))),
interp(~n()))
names(ret_ctgry_df) <- c(glbFeatsCategory,
#paste0(glb_rsp_var, ".abs.", label, ".sum"),
paste0("err.abs.", label, ".sum"),
paste0("err.abs.", label, ".mean"),
paste0(".n.", label))
ret_ctgry_df <- dplyr::ungroup(ret_ctgry_df)
#colSums(ret_ctgry_df[, -grep(glbFeatsCategory, names(ret_ctgry_df))])
return(ret_ctgry_df)
}
#print(colSums((ctgry_df <- myget_category_stats(obs_df=glbObsFit, mdl_id="", label="fit"))[, -grep(glbFeatsCategory, names(ctgry_df))]))
if (!is.null(glb_mdl_ensemble)) {
fit.models_2_chunk_df <- myadd_chunk(fit.models_2_chunk_df,
paste0("fit.models_2_", mdl_id_pfx), major.inc = TRUE,
label.minor = "ensemble")
mdl_id_pfx <- "Ensemble"
if (#(glb_is_regression) |
((glb_is_classification) & (!glb_is_binomial)))
stop("Ensemble models not implemented yet for multinomial classification")
mygetEnsembleAutoMdlIds <- function() {
tmp_models_df <- orderBy(get_model_sel_frmla(), glb_models_df)
row.names(tmp_models_df) <- tmp_models_df$id
mdl_threshold_pos <-
min(which(grepl("MFO|Random|Baseline", tmp_models_df$id))) - 1
mdlIds <- tmp_models_df$id[1:mdl_threshold_pos]
return(mdlIds[!grepl("Ensemble", mdlIds)])
}
if (glb_mdl_ensemble == "auto") {
glb_mdl_ensemble <- mygetEnsembleAutoMdlIds()
mdl_id_pfx <- paste0(mdl_id_pfx, ".auto")
} else if (grepl("^%<d-%", glb_mdl_ensemble)) {
glb_mdl_ensemble <- eval(parse(text =
str_trim(unlist(strsplit(glb_mdl_ensemble, "%<d-%"))[2])))
}
for (mdl_id in glb_mdl_ensemble) {
if (!(mdl_id %in% names(glb_models_lst))) {
warning("Model ", mdl_id, " in glb_model_ensemble not found !")
next
}
glbObsFit <- glb_get_predictions(df = glbObsFit, mdl_id, glb_rsp_var)
glbObsOOB <- glb_get_predictions(df = glbObsOOB, mdl_id, glb_rsp_var)
}
#mdl_id_pfx <- "Ensemble.RFE"; mdlId <- paste0(mdl_id_pfx, ".glmnet")
#glb_mdl_ensemble <- gsub(mygetPredictIds$value, "", grep("RFE\\.X\\.(?!Interact)", row.names(glb_featsimp_df), perl = TRUE, value = TRUE), fixed = TRUE)
#varImp(glb_models_lst[[mdlId]])
#cor_df <- data.frame(cor=cor(glbObsFit[, glb_rsp_var], glbObsFit[, paste(mygetPredictIds$value, glb_mdl_ensemble)], use="pairwise.complete.obs"))
#glbObsFit <- glb_get_predictions(df=glbObsFit, "Ensemble.glmnet", glb_rsp_var);print(colSums((ctgry_df <- myget_category_stats(obs_df=glbObsFit, mdl_id="Ensemble.glmnet", label="fit"))[, -grep(glbFeatsCategory, names(ctgry_df))]))
### bid0_sp
# Better than MFO; models.n=28; min.RMSE.fit=0.0521233; err.abs.fit.sum=7.3631895
# old: Top x from auto; models.n= 5; min.RMSE.fit=0.06311047; err.abs.fit.sum=9.5937080
# RFE only ; models.n=16; min.RMSE.fit=0.05148588; err.abs.fit.sum=7.2875091
# RFE subset only ;models.n= 5; min.RMSE.fit=0.06040702; err.abs.fit.sum=9.059088
# RFE subset only ;models.n= 9; min.RMSE.fit=0.05933167; err.abs.fit.sum=8.7421288
# RFE subset only ;models.n=15; min.RMSE.fit=0.0584607; err.abs.fit.sum=8.5902066
# RFE subset only ;models.n=17; min.RMSE.fit=0.05496899; err.abs.fit.sum=8.0170431
# RFE subset only ;models.n=18; min.RMSE.fit=0.05441577; err.abs.fit.sum=7.837223
# RFE subset only ;models.n=16; min.RMSE.fit=0.05441577; err.abs.fit.sum=7.837223
### bid0_sp
### bid1_sp
# "auto"; err.abs.fit.sum=76.699774; min.RMSE.fit=0.2186429
# "RFE.X.*"; err.abs.fit.sum=; min.RMSE.fit=0.221114
### bid1_sp
indepVar <- paste(mygetPredictIds(glb_rsp_var)$value, glb_mdl_ensemble, sep = "")
if (glb_is_classification)
indepVar <- paste(indepVar, ".prob", sep = "")
# Some models in glb_mdl_ensemble might not be fitted e.g. RFE.X.Interact
indepVar <- intersect(indepVar, names(glbObsFit))
# indepVar <- grep(mygetPredictIds(glb_rsp_var)$value, names(glbObsFit), fixed=TRUE, value=TRUE)
# if (glb_is_regression)
# indepVar <- indepVar[!grepl("(err\\.abs|accurate)$", indepVar)]
# if (glb_is_classification && glb_is_binomial)
# indepVar <- grep("prob$", indepVar, value=TRUE) else
# indepVar <- indepVar[!grepl("err$", indepVar)]
#rfe_fit_ens_results <- myrun_rfe(glbObsFit, indepVar)
for (method in c("glm", "glmnet")) {
for (trainControlMethod in
c("boot", "boot632", "cv", "repeatedcv"
#, "LOOCV" # tuneLength * nrow(fitDF)
, "LGOCV", "adaptive_cv"
#, "adaptive_boot" #error: adaptive$min should be less than 3
#, "adaptive_LGOCV" #error: adaptive$min should be less than 3
)) {
#sav_models_df <- glb_models_df; all.equal(sav_models_df, glb_models_df)
#glb_models_df <- sav_models_df; print(glb_models_df$id)
if ((method == "glm") && (trainControlMethod != "repeatedcv"))
# glm used only to identify outliers
next
ret_lst <- myfit_mdl(
mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = paste0(mdl_id_pfx, ".", trainControlMethod),
type = glb_model_type, tune.df = NULL,
trainControl.method = trainControlMethod,
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
}
dsp_models_df <- get_dsp_models_df()
}
if (is.null(glbMdlSelId))
glbMdlSelId <- dsp_models_df[1, "id"] else
print(sprintf("User specified selection: %s", glbMdlSelId)) ## [1] "User specified selection: All.X##rcv#glmnet"myprint_mdl(glb_sel_mdl <- glb_models_lst[[glbMdlSelId]])
## Length Class Mode
## a0 91 -none- numeric
## beta 21112 dgCMatrix S4
## df 91 -none- numeric
## dim 2 -none- numeric
## lambda 91 -none- numeric
## dev.ratio 91 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 232 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) .rnorm Edn.fctr.L
## 0.2182238650 -0.0043218147 0.0889974083
## Edn.fctr^6 Edn.fctr^7 Gender.fctrF
## 0.0094799038 0.0048448375 0.0172572894
## Gender.fctrM Hhold.fctrMKy Hhold.fctrPKn
## -0.0954525253 -0.0787132143 0.4769245380
## Hhold.fctrSKy Income.fctr.Q Income.fctr.C
## 0.0943955021 -0.1221098223 -0.0659690797
## Q100689.fctrYes Q101163.fctrDad Q101163.fctrMom
## 0.0937319604 -0.1215446266 0.0660995478
## Q101596.fctrYes Q102089.fctrRent Q102687.fctrYes
## -0.0123450142 0.0406874879 0.0264877074
## Q104996.fctrNo Q104996.fctrYes Q105655.fctrYes
## -0.0337954466 0.0101901384 -0.0114351855
## Q105840.fctrNo Q105840.fctrYes Q106042.fctrNo
## -0.0123695990 0.0344623775 -0.0630096832
## Q106388.fctrYes Q106389.fctrNo Q106997.fctrGr
## -0.0188230968 -0.0340393517 -0.0364878723
## Q107869.fctrNo Q108342.fctrOnline Q108754.fctrYes
## 0.0044655353 0.0509099257 -0.0376620607
## Q108855.fctrYes! Q108856.fctrSocialize Q109244.fctrNo
## -0.0210268035 -0.0245883944 -0.4487227152
## Q109244.fctrYes Q109367.fctrYes Q110740.fctrPC
## 0.9786872953 0.0173930011 -0.0794727701
## Q111220.fctrNo Q111220.fctrYes Q111848.fctrYes
## -0.0033922528 0.0585611159 0.0457539270
## Q112478.fctrNo Q113181.fctrNo Q113181.fctrYes
## -0.0246349466 0.1112819023 -0.1476035076
## Q113583.fctrTunes Q113992.fctrYes Q114517.fctrNo
## 0.0154543164 0.0051559413 0.0291348877
## Q115195.fctrNo Q115195.fctrYes Q115390.fctrYes
## -0.0078804951 0.0287640101 0.0480452601
## Q115610.fctrNo Q115611.fctrNo Q115611.fctrYes
## -0.0222477010 0.1250266333 -0.2789081127
## Q115899.fctrCs Q115899.fctrMe Q116197.fctrA.M.
## 0.0716304093 -0.0260904021 -0.0174322339
## Q116881.fctrHappy Q116881.fctrRight Q116953.fctrNo
## 0.0169108547 -0.1579213060 -0.0631621922
## Q118117.fctrYes Q118232.fctrId Q118233.fctrNo
## -0.0334356195 0.1000892607 -0.0512886740
## Q118892.fctrNo Q119851.fctrNo Q119851.fctrYes
## -0.0085291598 -0.0732053282 0.0864474832
## Q120012.fctrYes Q120014.fctrNo Q120014.fctrYes
## 0.0271682299 0.0120135238 -0.0072627910
## Q120194.fctrStudy first Q120379.fctrNo Q120379.fctrYes
## 0.0016623595 -0.0288424701 0.0752754524
## Q120472.fctrScience Q120650.fctrNo Q121011.fctrNo
## -0.0747816069 0.0068796862 -0.0032091223
## Q121011.fctrYes Q121699.fctrYes Q122120.fctrYes
## 0.0005825808 0.0566692057 -0.0723720439
## Q122771.fctrPt Q124122.fctrNo Q124742.fctrNo
## -0.0931571736 -0.0136270820 0.0359290161
## Q96024.fctrNo Q98059.fctrOnly-child Q98059.fctrYes
## 0.0025316228 -0.0291527328 0.0386035110
## Q98197.fctrNo Q98197.fctrYes Q98869.fctrNo
## 0.1597329673 -0.1087430705 0.2515168378
## Q99480.fctrNo Q99480.fctrYes Q99716.fctrYes
## 0.1232352423 -0.0539966633 0.0532365742
## YOB.Age.fctr.L YOB.Age.fctr.C YOB.Age.fctr^4
## 0.1045001488 -0.0057348189 0.0094887582
## YOB.Age.fctr^7 YOB.Age.fctr^8
## -0.0613013716 -0.1099161376
## [1] "max lambda < lambdaOpt:"
## (Intercept) .rnorm Edn.fctr.L
## 0.221417216 -0.006597013 0.090650240
## Edn.fctr^4 Edn.fctr^6 Edn.fctr^7
## -0.006212844 0.014671948 0.012263535
## Gender.fctrF Gender.fctrM Hhold.fctrMKy
## 0.011870040 -0.097301759 -0.085045637
## Hhold.fctrPKn Hhold.fctrSKy Income.fctr.Q
## 0.494037561 0.105977265 -0.128755036
## Income.fctr.C Q100689.fctrYes Q101162.fctrPessimist
## -0.075857022 0.101220202 -0.002204401
## Q101163.fctrDad Q101163.fctrMom Q101596.fctrYes
## -0.126578407 0.067730099 -0.016968414
## Q102089.fctrRent Q102687.fctrYes Q102906.fctrYes
## 0.043669337 0.032907509 -0.007762629
## Q104996.fctrNo Q104996.fctrYes Q105655.fctrYes
## -0.037493190 0.015130905 -0.016975835
## Q105840.fctrNo Q105840.fctrYes Q106042.fctrNo
## -0.010171139 0.036925726 -0.066503426
## Q106388.fctrYes Q106389.fctrNo Q106997.fctrGr
## -0.022943776 -0.040627101 -0.043079556
## Q107869.fctrNo Q108342.fctrOnline Q108754.fctrYes
## 0.010479401 0.056696098 -0.044397972
## Q108855.fctrYes! Q108856.fctrSocialize Q109244.fctrNo
## -0.025021908 -0.031459608 -0.456280408
## Q109244.fctrYes Q109367.fctrYes Q110740.fctrMac
## 1.002758973 0.019318706 0.002156371
## Q110740.fctrPC Q111220.fctrNo Q111220.fctrYes
## -0.084754385 -0.007032618 0.064044977
## Q111848.fctrYes Q112270.fctrNo Q112478.fctrNo
## 0.052138649 0.003287377 -0.029376738
## Q113181.fctrNo Q113181.fctrYes Q113583.fctrTunes
## 0.112453535 -0.151021176 0.019871028
## Q113992.fctrYes Q114517.fctrNo Q115195.fctrNo
## 0.011251605 0.035545764 -0.011439291
## Q115195.fctrYes Q115390.fctrYes Q115610.fctrNo
## 0.031093303 0.054301606 -0.029943924
## Q115611.fctrNo Q115611.fctrYes Q115899.fctrCs
## 0.125263509 -0.286364102 0.077026205
## Q115899.fctrMe Q116197.fctrA.M. Q116881.fctrHappy
## -0.028044295 -0.024382405 0.021409011
## Q116881.fctrRight Q116953.fctrNo Q118117.fctrYes
## -0.161417346 -0.070435474 -0.035874178
## Q118232.fctrId Q118233.fctrNo Q118892.fctrNo
## 0.108484869 -0.058777096 -0.010341717
## Q119851.fctrNo Q119851.fctrYes Q120012.fctrYes
## -0.076983210 0.090596907 0.032055116
## Q120014.fctrNo Q120014.fctrYes Q120194.fctrStudy first
## 0.014190240 -0.009626995 0.005272177
## Q120379.fctrNo Q120379.fctrYes Q120472.fctrScience
## -0.032254122 0.081003638 -0.079944132
## Q120650.fctrNo Q121011.fctrNo Q121011.fctrYes
## 0.016571439 -0.004007171 0.002867060
## Q121699.fctrYes Q122120.fctrYes Q122771.fctrPt
## 0.061730344 -0.080375537 -0.101563391
## Q123621.fctrYes Q124122.fctrNo Q124742.fctrNo
## -0.005710537 -0.018809312 0.044885981
## Q96024.fctrNo Q98059.fctrOnly-child Q98059.fctrYes
## 0.007267349 -0.042172589 0.046420210
## Q98197.fctrNo Q98197.fctrYes Q98869.fctrNo
## 0.163217987 -0.111310168 0.261203168
## Q99480.fctrNo Q99480.fctrYes Q99716.fctrYes
## 0.127854410 -0.060882172 0.055399976
## YOB.Age.fctr.L YOB.Age.fctr.C YOB.Age.fctr^4
## 0.115326080 -0.015897589 0.014310212
## YOB.Age.fctr^7 YOB.Age.fctr^8
## -0.072623853 -0.121236319## [1] TRUE# From here to save(), this should all be in one function
# these are executed in the same seq twice more:
# fit.data.training & predict.data.new chunks
print(sprintf("%s fit prediction diagnostics:", glbMdlSelId))## [1] "All.X##rcv#glmnet fit prediction diagnostics:"glbObsFit <- glb_get_predictions(df = glbObsFit, mdl_id = glbMdlSelId,
rsp_var = glb_rsp_var)
print(sprintf("%s OOB prediction diagnostics:", glbMdlSelId))## [1] "All.X##rcv#glmnet OOB prediction diagnostics:"glbObsOOB <- glb_get_predictions(df = glbObsOOB, mdl_id = glbMdlSelId,
rsp_var = glb_rsp_var)
print(glb_featsimp_df <- myget_feats_importance(mdl = glb_sel_mdl, featsimp_df = NULL))## All.X..rcv.glmnet.imp imp
## Q109244.fctrYes 100.0000000 100.0000000
## Hhold.fctrPKn 49.1661885 49.1661885
## Q109244.fctrNo 45.5681943 45.5681943
## Q115611.fctrYes 28.5463664 28.5463664
## Q98869.fctrNo 25.9823593 25.9823593
## Q98197.fctrNo 16.2852705 16.2852705
## Q116881.fctrRight 16.1046523 16.1046523
## Q113181.fctrYes 15.0645836 15.0645836
## Income.fctr.Q 12.7713107 12.7713107
## Q99480.fctrNo 12.7202759 12.7202759
## Q101163.fctrDad 12.5844125 12.5844125
## Q115611.fctrNo 12.5454803 12.5454803
## YOB.Age.fctr^8 11.9275685 11.9275685
## YOB.Age.fctr.L 11.3449880 11.3449880
## Q113181.fctrNo 11.2439730 11.2439730
## Q98197.fctrYes 11.1024216 11.1024216
## Q118232.fctrId 10.7065918 10.7065918
## Hhold.fctrSKy 10.3937136 10.3937136
## Q122771.fctrPt 10.0129285 10.0129285
## Q100689.fctrYes 9.9963048 9.9963048
## Gender.fctrM 9.7128176 9.7128176
## Edn.fctr.L 9.0502064 9.0502064
## Q119851.fctrYes 8.9965611 8.9965611
## Hhold.fctrMKy 8.3981484 8.3981484
## Q110740.fctrPC 8.3892982 8.3892982
## Q120379.fctrYes 8.0048736 8.0048736
## Q120472.fctrScience 7.9096663 7.9096663
## Q122120.fctrYes 7.8979239 7.8979239
## Q119851.fctrNo 7.6398025 7.6398025
## Q115899.fctrCs 7.6128082 7.6128082
## Income.fctr.C 7.4087582 7.4087582
## YOB.Age.fctr^7 7.0570750 7.0570750
## Q116953.fctrNo 6.9161634 6.9161634
## Q101163.fctrMom 6.7542846 6.7542846
## Q106042.fctrNo 6.5953376 6.5953376
## Q111220.fctrYes 6.3105242 6.3105242
## Q121699.fctrYes 6.0868013 6.0868013
## Q99480.fctrYes 5.9665271 5.9665271
## Q118233.fctrNo 5.7439564 5.7439564
## Q108342.fctrOnline 5.5683963 5.5683963
## Q99716.fctrYes 5.5086291 5.5086291
## Q115390.fctrYes 5.3193973 5.3193973
## Q111848.fctrYes 5.1002085 5.1002085
## Q98059.fctrYes 4.4995773 4.4995773
## Q124742.fctrNo 4.3238031 4.3238031
## Q108754.fctrYes 4.3178810 4.3178810
## Q102089.fctrRent 4.3175100 4.3175100
## Q106997.fctrGr 4.1885801 4.1885801
## Q98059.fctrOnly-child 3.9733449 3.9733449
## Q106389.fctrNo 3.9429465 3.9429465
## Q104996.fctrNo 3.6848756 3.6848756
## Q105840.fctrYes 3.6519038 3.6519038
## Q118117.fctrYes 3.5470296 3.5470296
## Q114517.fctrNo 3.4372729 3.4372729
## Q102687.fctrYes 3.1727753 3.1727753
## Q120379.fctrNo 3.1655121 3.1655121
## Q120012.fctrYes 3.1170322 3.1170322
## Q115195.fctrYes 3.0701510 3.0701510
## Q108856.fctrSocialize 3.0189776 3.0189776
## Q112478.fctrNo 2.8514946 2.8514946
## Q115610.fctrNo 2.8511607 2.8511607
## Q115899.fctrMe 2.7719360 2.7719360
## Q108855.fctrYes! 2.4296335 2.4296335
## Q116197.fctrA.M. 2.3083900 2.3083900
## Q106388.fctrYes 2.2189974 2.2189974
## Q116881.fctrHappy 2.0579273 2.0579273
## Q113583.fctrTunes 1.9054136 1.9054136
## Q109367.fctrYes 1.8982707 1.8982707
## Q124122.fctrNo 1.7842304 1.7842304
## Q101596.fctrYes 1.6106039 1.6106039
## Q105655.fctrYes 1.5936012 1.5936012
## Q120650.fctrNo 1.4727730 1.4727730
## Q104996.fctrYes 1.4203649 1.4203649
## YOB.Age.fctr.C 1.3961476 1.3961476
## Q120014.fctrNo 1.3795969 1.3795969
## Edn.fctr^6 1.3695208 1.3695208
## YOB.Age.fctr^4 1.3404486 1.3404486
## Gender.fctrF 1.2934789 1.2934789
## Edn.fctr^7 1.0851442 1.0851442
## Q115195.fctrNo 1.0772420 1.0772420
## Q105840.fctrNo 1.0615732 1.0615732
## Q113992.fctrYes 1.0093567 1.0093567
## Q118892.fctrNo 1.0010616 1.0010616
## Q107869.fctrNo 0.9335726 0.9335726
## Q120014.fctrYes 0.9187812 0.9187812
## Q96024.fctrNo 0.6364877 0.6364877
## Q111220.fctrNo 0.6341624 0.6341624
## Q102906.fctrYes 0.6275475 0.6275475
## .rnorm 0.6169315 0.6169315
## Edn.fctr^4 0.5022596 0.5022596
## Q123621.fctrYes 0.4616520 0.4616520
## Q120194.fctrStudy first 0.4583760 0.4583760
## Q121011.fctrNo 0.3860357 0.3860357
## Q112270.fctrNo 0.2657586 0.2657586
## Q121011.fctrYes 0.2430506 0.2430506
## Q101162.fctrPessimist 0.1782085 0.1782085
## Q110740.fctrMac 0.1743257 0.1743257
## Edn.fctr.Q 0.0000000 0.0000000
## Edn.fctr.C 0.0000000 0.0000000
## Edn.fctr^5 0.0000000 0.0000000
## Hhold.fctrMKn 0.0000000 0.0000000
## Hhold.fctrPKy 0.0000000 0.0000000
## Hhold.fctrSKn 0.0000000 0.0000000
## Income.fctr.L 0.0000000 0.0000000
## Income.fctr^4 0.0000000 0.0000000
## Income.fctr^5 0.0000000 0.0000000
## Income.fctr^6 0.0000000 0.0000000
## Q100010.fctrNo 0.0000000 0.0000000
## Q100010.fctrYes 0.0000000 0.0000000
## Q100562.fctrNo 0.0000000 0.0000000
## Q100562.fctrYes 0.0000000 0.0000000
## Q100680.fctrNo 0.0000000 0.0000000
## Q100680.fctrYes 0.0000000 0.0000000
## Q100689.fctrNo 0.0000000 0.0000000
## Q101162.fctrOptimist 0.0000000 0.0000000
## Q101596.fctrNo 0.0000000 0.0000000
## Q102089.fctrOwn 0.0000000 0.0000000
## Q102289.fctrNo 0.0000000 0.0000000
## Q102289.fctrYes 0.0000000 0.0000000
## Q102674.fctrNo 0.0000000 0.0000000
## Q102674.fctrYes 0.0000000 0.0000000
## Q102687.fctrNo 0.0000000 0.0000000
## Q102906.fctrNo 0.0000000 0.0000000
## Q103293.fctrNo 0.0000000 0.0000000
## Q103293.fctrYes 0.0000000 0.0000000
## Q105655.fctrNo 0.0000000 0.0000000
## Q106042.fctrYes 0.0000000 0.0000000
## Q106272.fctrNo 0.0000000 0.0000000
## Q106272.fctrYes 0.0000000 0.0000000
## Q106388.fctrNo 0.0000000 0.0000000
## Q106389.fctrYes 0.0000000 0.0000000
## Q106993.fctrNo 0.0000000 0.0000000
## Q106993.fctrYes 0.0000000 0.0000000
## Q106997.fctrYy 0.0000000 0.0000000
## Q107491.fctrNo 0.0000000 0.0000000
## Q107491.fctrYes 0.0000000 0.0000000
## Q107869.fctrYes 0.0000000 0.0000000
## Q108342.fctrIn-person 0.0000000 0.0000000
## Q108343.fctrNo 0.0000000 0.0000000
## Q108343.fctrYes 0.0000000 0.0000000
## Q108617.fctrNo 0.0000000 0.0000000
## Q108617.fctrYes 0.0000000 0.0000000
## Q108754.fctrNo 0.0000000 0.0000000
## Q108855.fctrUmm... 0.0000000 0.0000000
## Q108856.fctrSpace 0.0000000 0.0000000
## Q108950.fctrCautious 0.0000000 0.0000000
## Q108950.fctrRisk-friendly 0.0000000 0.0000000
## Q109367.fctrNo 0.0000000 0.0000000
## Q111580.fctrDemanding 0.0000000 0.0000000
## Q111580.fctrSupportive 0.0000000 0.0000000
## Q111848.fctrNo 0.0000000 0.0000000
## Q112270.fctrYes 0.0000000 0.0000000
## Q112478.fctrYes 0.0000000 0.0000000
## Q112512.fctrNo 0.0000000 0.0000000
## Q112512.fctrYes 0.0000000 0.0000000
## Q113583.fctrTalk 0.0000000 0.0000000
## Q113584.fctrPeople 0.0000000 0.0000000
## Q113584.fctrTechnology 0.0000000 0.0000000
## Q113992.fctrNo 0.0000000 0.0000000
## Q114152.fctrNo 0.0000000 0.0000000
## Q114152.fctrYes 0.0000000 0.0000000
## Q114386.fctrMysterious 0.0000000 0.0000000
## Q114386.fctrTMI 0.0000000 0.0000000
## Q114517.fctrYes 0.0000000 0.0000000
## Q114748.fctrNo 0.0000000 0.0000000
## Q114748.fctrYes 0.0000000 0.0000000
## Q114961.fctrNo 0.0000000 0.0000000
## Q114961.fctrYes 0.0000000 0.0000000
## Q115390.fctrNo 0.0000000 0.0000000
## Q115602.fctrNo 0.0000000 0.0000000
## Q115602.fctrYes 0.0000000 0.0000000
## Q115610.fctrYes 0.0000000 0.0000000
## Q115777.fctrEnd 0.0000000 0.0000000
## Q115777.fctrStart 0.0000000 0.0000000
## Q116197.fctrP.M. 0.0000000 0.0000000
## Q116441.fctrNo 0.0000000 0.0000000
## Q116441.fctrYes 0.0000000 0.0000000
## Q116448.fctrNo 0.0000000 0.0000000
## Q116448.fctrYes 0.0000000 0.0000000
## Q116601.fctrNo 0.0000000 0.0000000
## Q116601.fctrYes 0.0000000 0.0000000
## Q116797.fctrNo 0.0000000 0.0000000
## Q116797.fctrYes 0.0000000 0.0000000
## Q116953.fctrYes 0.0000000 0.0000000
## Q117186.fctrCool headed 0.0000000 0.0000000
## Q117186.fctrHot headed 0.0000000 0.0000000
## Q117193.fctrOdd hours 0.0000000 0.0000000
## Q117193.fctrStandard hours 0.0000000 0.0000000
## Q118117.fctrNo 0.0000000 0.0000000
## Q118232.fctrPr 0.0000000 0.0000000
## Q118233.fctrYes 0.0000000 0.0000000
## Q118237.fctrNo 0.0000000 0.0000000
## Q118237.fctrYes 0.0000000 0.0000000
## Q118892.fctrYes 0.0000000 0.0000000
## Q119334.fctrNo 0.0000000 0.0000000
## Q119334.fctrYes 0.0000000 0.0000000
## Q119650.fctrGiving 0.0000000 0.0000000
## Q119650.fctrReceiving 0.0000000 0.0000000
## Q120012.fctrNo 0.0000000 0.0000000
## Q120194.fctrTry first 0.0000000 0.0000000
## Q120472.fctrArt 0.0000000 0.0000000
## Q120650.fctrYes 0.0000000 0.0000000
## Q120978.fctrNo 0.0000000 0.0000000
## Q120978.fctrYes 0.0000000 0.0000000
## Q121699.fctrNo 0.0000000 0.0000000
## Q121700.fctrNo 0.0000000 0.0000000
## Q121700.fctrYes 0.0000000 0.0000000
## Q122120.fctrNo 0.0000000 0.0000000
## Q122769.fctrNo 0.0000000 0.0000000
## Q122769.fctrYes 0.0000000 0.0000000
## Q122770.fctrNo 0.0000000 0.0000000
## Q122770.fctrYes 0.0000000 0.0000000
## Q122771.fctrPc 0.0000000 0.0000000
## Q123464.fctrNo 0.0000000 0.0000000
## Q123464.fctrYes 0.0000000 0.0000000
## Q123621.fctrNo 0.0000000 0.0000000
## Q124122.fctrYes 0.0000000 0.0000000
## Q124742.fctrYes 0.0000000 0.0000000
## Q96024.fctrYes 0.0000000 0.0000000
## Q98078.fctrNo 0.0000000 0.0000000
## Q98078.fctrYes 0.0000000 0.0000000
## Q98578.fctrNo 0.0000000 0.0000000
## Q98578.fctrYes 0.0000000 0.0000000
## Q98869.fctrYes 0.0000000 0.0000000
## Q99581.fctrNo 0.0000000 0.0000000
## Q99581.fctrYes 0.0000000 0.0000000
## Q99716.fctrNo 0.0000000 0.0000000
## Q99982.fctrCheck! 0.0000000 0.0000000
## Q99982.fctrNope 0.0000000 0.0000000
## YOB.Age.fctr.Q 0.0000000 0.0000000
## YOB.Age.fctr^5 0.0000000 0.0000000
## YOB.Age.fctr^6 0.0000000 0.0000000#mdl_id <-"RFE.X.glmnet"; glb_featsimp_df <- myget_feats_importance(glb_models_lst[[mdl_id]], glb_featsimp_df); glb_featsimp_df[, paste0(mdl_id, ".imp")] <- glb_featsimp_df$imp; print(glb_featsimp_df)
#print(head(sbst_featsimp_df <- subset(glb_featsimp_df, is.na(RFE.X.glmnet.imp) | (abs(RFE.X.YeoJohnson.glmnet.imp - RFE.X.glmnet.imp) > 0.0001), select=-imp)))
#print(orderBy(~ -cor.y.abs, subset(glb_feats_df, id %in% c(row.names(sbst_featsimp_df), "startprice.dcm1.is9", "D.weight.post.stop.sum"))))
# Used again in fit.data.training & predict.data.new chunks
glb_analytics_diag_plots <- function(obs_df, mdl_id, prob_threshold=NULL) {
if (!is.null(featsimp_df <- glb_featsimp_df)) {
featsimp_df$feat <- gsub("`(.*?)`", "\\1", row.names(featsimp_df))
featsimp_df$feat.interact <- gsub("(.*?):(.*)", "\\2", featsimp_df$feat)
featsimp_df$feat <- gsub("(.*?):(.*)", "\\1", featsimp_df$feat)
featsimp_df$feat.interact <-
ifelse(featsimp_df$feat.interact == featsimp_df$feat,
NA, featsimp_df$feat.interact)
featsimp_df$feat <-
gsub("(.*?)\\.fctr(.*)", "\\1\\.fctr", featsimp_df$feat)
featsimp_df$feat.interact <-
gsub("(.*?)\\.fctr(.*)", "\\1\\.fctr", featsimp_df$feat.interact)
featsimp_df <- orderBy(~ -imp.max,
summaryBy(imp ~ feat + feat.interact, data=featsimp_df,
FUN=max))
#rex_str=":(.*)"; txt_vctr=tail(featsimp_df$feat); ret_lst <- regexec(rex_str, txt_vctr); ret_lst <- regmatches(txt_vctr, ret_lst); ret_vctr <- sapply(1:length(ret_lst), function(pos_ix) ifelse(length(ret_lst[[pos_ix]]) > 0, ret_lst[[pos_ix]], "")); print(ret_vctr <- ret_vctr[ret_vctr != ""])
featsimp_df <- subset(featsimp_df, !is.na(imp.max))
if (nrow(featsimp_df) > 5) {
warning("Limiting important feature scatter plots to 5 out of ",
nrow(featsimp_df))
featsimp_df <- head(featsimp_df, 5)
}
# if (!all(is.na(featsimp_df$feat.interact)))
# stop("not implemented yet")
rsp_var_out <- mygetPredictIds(glb_rsp_var, mdl_id)$value
for (var in featsimp_df$feat) {
plot_df <- melt(obs_df, id.vars = var,
measure.vars = c(glb_rsp_var, rsp_var_out))
print(myplot_scatter(plot_df, var, "value", colorcol_name = "variable",
facet_colcol_name = "variable", jitter = TRUE) +
guides(color = FALSE))
}
}
if (glb_is_regression) {
if (is.null(featsimp_df) || (nrow(featsimp_df) == 0))
warning("No important features in glb_fin_mdl") else
print(myplot_prediction_regression(df=obs_df,
feat_x=ifelse(nrow(featsimp_df) > 1, featsimp_df$feat[2],
".rownames"),
feat_y=featsimp_df$feat[1],
rsp_var=glb_rsp_var, rsp_var_out=rsp_var_out,
id_vars=glbFeatsId)
# + facet_wrap(reformulate(featsimp_df$feat[2])) # if [1 or 2] is a factor
# + geom_point(aes_string(color="<col_name>.fctr")) # to color the plot
)
}
if (glb_is_classification) {
require(lazyeval)
if (is.null(featsimp_df) || (nrow(featsimp_df) == 0))
warning("No features in selected model are statistically important")
else print(myplot_prediction_classification(df = obs_df,
feat_x = ifelse(nrow(featsimp_df) > 1,
featsimp_df$feat[2], ".rownames"),
feat_y = featsimp_df$feat[1],
rsp_var = glb_rsp_var,
rsp_var_out = rsp_var_out,
id_vars = glbFeatsId,
prob_threshold = prob_threshold))
}
}
if (glb_is_classification && glb_is_binomial)
glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id = glbMdlSelId,
prob_threshold = glb_models_df[glb_models_df$id == glbMdlSelId,
"opt.prob.threshold.OOB"]) else
glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id = glbMdlSelId) ## Warning in glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id =
## glbMdlSelId, : Limiting important feature scatter plots to 5 out of 107
## Loading required package: lazyeval
## [1] "Min/Max Boundaries: "
## [1] "Inaccurate: "
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 1 1309 D 0.1977846
## 2 2641 D 0.1981250
## 3 66 D 0.2022717
## 4 1393 D 0.2128637
## 5 697 D 0.2210805
## 6 3512 D 0.2214342
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 1 R TRUE
## 2 R TRUE
## 3 R TRUE
## 4 R TRUE
## 5 R TRUE
## 6 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs Party.fctr.All.X..rcv.glmnet.is.acc
## 1 0.8022154 FALSE
## 2 0.8018750 FALSE
## 3 0.7977283 FALSE
## 4 0.7871363 FALSE
## 5 0.7789195 FALSE
## 6 0.7785658 FALSE
## Party.fctr.All.X..rcv.glmnet.accurate Party.fctr.All.X..rcv.glmnet.error
## 1 FALSE -0.7522154
## 2 FALSE -0.7518750
## 3 FALSE -0.7477283
## 4 FALSE -0.7371363
## 5 FALSE -0.7289195
## 6 FALSE -0.7285658
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 134 2440 D 0.4408080
## 203 6719 D 0.4825200
## 280 214 D 0.5204347
## 340 6793 D 0.5525426
## 560 579 D 0.8560266
## 572 2421 D 0.8759315
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 134 R TRUE
## 203 R TRUE
## 280 R TRUE
## 340 R TRUE
## 560 R TRUE
## 572 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs
## 134 0.5591920
## 203 0.5174800
## 280 0.4795653
## 340 0.4474574
## 560 0.1439734
## 572 0.1240685
## Party.fctr.All.X..rcv.glmnet.is.acc
## 134 FALSE
## 203 FALSE
## 280 FALSE
## 340 FALSE
## 560 FALSE
## 572 FALSE
## Party.fctr.All.X..rcv.glmnet.accurate
## 134 FALSE
## 203 FALSE
## 280 FALSE
## 340 FALSE
## 560 FALSE
## 572 FALSE
## Party.fctr.All.X..rcv.glmnet.error
## 134 -0.50919197
## 203 -0.46748000
## 280 -0.42956535
## 340 -0.39745741
## 560 -0.09397338
## 572 -0.07406845
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 586 1287 D 0.9072604
## 587 2385 D 0.9116701
## 588 3118 D 0.9151838
## 589 5082 D 0.9178451
## 590 644 D 0.9253588
## 591 2125 D 0.9277809
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 586 R TRUE
## 587 R TRUE
## 588 R TRUE
## 589 R TRUE
## 590 R TRUE
## 591 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs
## 586 0.09273960
## 587 0.08832992
## 588 0.08481624
## 589 0.08215488
## 590 0.07464121
## 591 0.07221909
## Party.fctr.All.X..rcv.glmnet.is.acc
## 586 FALSE
## 587 FALSE
## 588 FALSE
## 589 FALSE
## 590 FALSE
## 591 FALSE
## Party.fctr.All.X..rcv.glmnet.accurate
## 586 FALSE
## 587 FALSE
## 588 FALSE
## 589 FALSE
## 590 FALSE
## 591 FALSE
## Party.fctr.All.X..rcv.glmnet.error
## 586 -0.04273960
## 587 -0.03832992
## 588 -0.03481624
## 589 -0.03215488
## 590 -0.02464121
## 591 -0.02221909
if (!is.null(glbFeatsCategory)) {
glbLvlCategory <- merge(glbLvlCategory,
myget_category_stats(obs_df = glbObsFit, mdl_id = glbMdlSelId,
label = "fit"),
by = glbFeatsCategory, all = TRUE)
row.names(glbLvlCategory) <- glbLvlCategory[, glbFeatsCategory]
glbLvlCategory <- merge(glbLvlCategory,
myget_category_stats(obs_df = glbObsOOB, mdl_id = glbMdlSelId,
label="OOB"),
#by=glbFeatsCategory, all=TRUE) glb_ctgry-df already contains .n.OOB ?
all = TRUE)
row.names(glbLvlCategory) <- glbLvlCategory[, glbFeatsCategory]
if (any(grepl("OOB", glbMdlMetricsEval)))
print(orderBy(~-err.abs.OOB.mean, glbLvlCategory)) else
print(orderBy(~-err.abs.fit.mean, glbLvlCategory))
print(colSums(glbLvlCategory[, -grep(glbFeatsCategory, names(glbLvlCategory))]))
}## Q109244.fctr .n.OOB .n.Fit .n.Tst .freqRatio.Fit .freqRatio.OOB
## No No 498 1961 622 0.4403773 0.4466368
## NA NA 438 1746 547 0.3920952 0.3928251
## Yes Yes 179 746 223 0.1675275 0.1605381
## .freqRatio.Tst err.abs.fit.sum err.abs.fit.mean .n.fit err.abs.OOB.sum
## No 0.4468391 881.0781 0.4493004 1961 243.08985
## NA 0.3929598 829.2116 0.4749207 1746 211.31349
## Yes 0.1602011 199.1027 0.2668937 746 83.86404
## err.abs.OOB.mean
## No 0.4881322
## NA 0.4824509
## Yes 0.4685142
## .n.OOB .n.Fit .n.Tst .freqRatio.Fit
## 1115.000000 4453.000000 1392.000000 1.000000
## .freqRatio.OOB .freqRatio.Tst err.abs.fit.sum err.abs.fit.mean
## 1.000000 1.000000 1909.392454 1.191115
## .n.fit err.abs.OOB.sum err.abs.OOB.mean
## 4453.000000 538.267380 1.439097write.csv(glbObsOOB[, c(glbFeatsId,
grep(glb_rsp_var, names(glbObsOOB), fixed=TRUE, value=TRUE))],
paste0(gsub(".", "_", paste0(glbOut$pfx, glbMdlSelId), fixed=TRUE),
"_OOBobs.csv"), row.names=FALSE)
fit.models_2_chunk_df <-
myadd_chunk(NULL, "fit.models_2_bgn", label.minor = "teardown")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_2_bgn 1 0 teardown 273.66 NA NAglb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc=FALSE)## label step_major step_minor label_minor bgn end elapsed
## 6 fit.models 4 2 2 260.521 273.671 13.15
## 7 fit.models 4 3 3 273.672 NA NA# if (sum(is.na(glbObsAll$D.P.http)) > 0)
# stop("fit.models_3: Why is this happening ?")
#stop(here"); glb2Sav()
sync_glb_obs_df <- function() {
# Merge or cbind ?
for (col in setdiff(names(glbObsFit), names(glbObsTrn)))
glbObsTrn[glbObsTrn$.lcn == "Fit", col] <<- glbObsFit[, col]
for (col in setdiff(names(glbObsFit), names(glbObsAll)))
glbObsAll[glbObsAll$.lcn == "Fit", col] <<- glbObsFit[, col]
if (all(is.na(glbObsNew[, glb_rsp_var])))
for (col in setdiff(names(glbObsOOB), names(glbObsTrn)))
glbObsTrn[glbObsTrn$.lcn == "OOB", col] <<- glbObsOOB[, col]
for (col in setdiff(names(glbObsOOB), names(glbObsAll)))
glbObsAll[glbObsAll$.lcn == "OOB", col] <<- glbObsOOB[, col]
}
sync_glb_obs_df()
print(setdiff(names(glbObsNew), names(glbObsAll)))## character(0)replay.petrisim(pn = glb_analytics_pn,
replay.trans = (glb_analytics_avl_objs <- c(glb_analytics_avl_objs,
"model.selected")), flip_coord = TRUE)## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: model.selected
## 1.0000 3 2 1 0 0
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.data.training", major.inc = TRUE)## label step_major step_minor label_minor bgn end
## 7 fit.models 4 3 3 273.672 278.319
## 8 fit.data.training 5 0 0 278.319 NA
## elapsed
## 7 4.647
## 8 NAStep 5.0: fit data training
#load(paste0(glb_inp_pfx, "dsk.RData"))
if (!is.null(glbMdlFinId) && (glbMdlFinId %in% names(glb_models_lst))) {
warning("Final model same as user selected model")
glb_fin_mdl <- glb_models_lst[[glbMdlFinId]]
} else
# if (nrow(glbObsFit) + length(glbObsFitOutliers) == nrow(glbObsTrn))
if (!all(is.na(glbObsNew[, glb_rsp_var])))
{
warning("Final model same as glbMdlSelId")
glbMdlFinId <- paste0("Final.", glbMdlSelId)
glb_fin_mdl <- glb_sel_mdl
glb_models_lst[[glbMdlFinId]] <- glb_fin_mdl
mdlDf <- glb_models_df[glb_models_df$id == glbMdlSelId, ]
mdlDf$id <- glbMdlFinId
glb_models_df <- rbind(glb_models_df, mdlDf)
} else {
if (grepl("RFE\\.X", names(glbMdlFamilies))) {
indepVar <- mygetIndepVar(glb_feats_df)
rfe_trn_results <-
myrun_rfe(glbObsTrn, indepVar, glbRFESizes[["Final"]])
if (!isTRUE(all.equal(sort(predictors(rfe_trn_results)),
sort(predictors(rfe_fit_results))))) {
print("Diffs predictors(rfe_trn_results) vs. predictors(rfe_fit_results):")
print(setdiff(predictors(rfe_trn_results), predictors(rfe_fit_results)))
print("Diffs predictors(rfe_fit_results) vs. predictors(rfe_trn_results):")
print(setdiff(predictors(rfe_fit_results), predictors(rfe_trn_results)))
}
}
# }
if (grepl("Ensemble", glbMdlSelId)) {
# Find which models are relevant
mdlimp_df <- subset(myget_feats_importance(glb_sel_mdl), imp > 5)
# Fit selected models on glbObsTrn
for (mdl_id in gsub(".prob", "",
gsub(mygetPredictIds(glb_rsp_var)$value, "", row.names(mdlimp_df), fixed = TRUE),
fixed = TRUE)) {
mdl_id_components <- unlist(strsplit(mdl_id, "[.]"))
mdlIdPfx <- paste0(c(head(mdl_id_components, -1), "Train"),
collapse = ".")
if (grepl("RFE\\.X\\.", mdlIdPfx))
mdlIndepVars <- myadjustInteractionFeats(glb_feats_df, myextract_actual_feats(
predictors(rfe_trn_results))) else
mdlIndepVars <- trim(unlist(
strsplit(glb_models_df[glb_models_df$id == mdl_id, "feats"], "[,]")))
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdlIdPfx,
type = glb_model_type, tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = tail(mdl_id_components, 1))),
indepVar = mdlIndepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsTrn, OOB_df = NULL)
glbObsTrn <- glb_get_predictions(df = glbObsTrn,
mdl_id = tail(glb_models_df$id, 1),
rsp_var = glb_rsp_var,
prob_threshold_def =
subset(glb_models_df, id == mdl_id)$opt.prob.threshold.OOB)
glbObsNew <- glb_get_predictions(df = glbObsNew,
mdl_id = tail(glb_models_df$id, 1),
rsp_var = glb_rsp_var,
prob_threshold_def =
subset(glb_models_df, id == mdl_id)$opt.prob.threshold.OOB)
}
}
# "Final" model
if ((model_method <- glb_sel_mdl$method) == "custom")
# get actual method from the mdl_id
model_method <- tail(unlist(strsplit(glbMdlSelId, "[.]")), 1)
if (grepl("Ensemble", glbMdlSelId)) {
# Find which models are relevant
mdlimp_df <- subset(myget_feats_importance(glb_sel_mdl), imp > 5)
if (glb_is_classification && glb_is_binomial)
indepVar <- gsub("(.*)\\.(.*)\\.prob", "\\1\\.Train\\.\\2\\.prob",
row.names(mdlimp_df)) else
indepVar <- gsub("(.*)\\.(.*)", "\\1\\.Train\\.\\2",
row.names(mdlimp_df))
} else
if (grepl("RFE.X", glbMdlSelId, fixed = TRUE)) {
indepVar <- myextract_actual_feats(predictors(rfe_trn_results))
} else indepVar <-
trim(unlist(strsplit(glb_models_df[glb_models_df$id ==
glbMdlSelId
, "feats"], "[,]")))
if (!is.null(glb_preproc_methods) &&
((match_pos <- regexpr(gsub(".", "\\.",
paste(glb_preproc_methods, collapse = "|"),
fixed = TRUE), glbMdlSelId)) != -1))
ths_preProcess <- str_sub(glbMdlSelId, match_pos,
match_pos + attr(match_pos, "match.length") - 1) else
ths_preProcess <- NULL
mdl_id_pfx <- ifelse(grepl("Ensemble", glbMdlSelId),
"Final.Ensemble", "Final")
trnobs_df <- glbObsTrn
if (!is.null(glbObsTrnOutliers[[mdl_id_pfx]])) {
trnobs_df <- glbObsTrn[!(glbObsTrn[, glbFeatsId] %in% glbObsTrnOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsTrn) - nrow(trnobs_df)))
print(setdiff(glbObsTrn[, glbFeatsId], trnobs_df[, glbFeatsId]))
}
# Force fitting of Final.glm to identify outliers
method_vctr <- unique(c(myparseMdlId(glbMdlSelId)$alg, glbMdlFamilies[["Final"]]))
for (method in method_vctr) {
#source("caret_nominalTrainWorkflow.R")
# glmnet requires at least 2 indep vars
if ((length(indepVar) == 1) && (method %in% "glmnet"))
next
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdl_id_pfx,
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method,
train.preProcess = ths_preProcess)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = trnobs_df, OOB_df = NULL)
if ((length(method_vctr) == 1) || (method != "glm")) {
glb_fin_mdl <- glb_models_lst[[length(glb_models_lst)]]
glbMdlFinId <- glb_models_df[length(glb_models_lst), "id"]
}
}
}## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Final##rcv#glmnet"
## [1] " indepVar: Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr"
## [1] "myfit_mdl: setup complete: 0.712000 secs"
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.775, lambda = 0.0113 on full training set
## [1] "myfit_mdl: train complete: 26.434000 secs"
## Length Class Mode
## a0 77 -none- numeric
## beta 17864 dgCMatrix S4
## df 77 -none- numeric
## dim 2 -none- numeric
## lambda 77 -none- numeric
## dev.ratio 77 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 2 -none- character
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 232 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 2 -none- character
## [1] "min lambda > lambdaOpt:"
## (Intercept) Edn.fctr.L Gender.fctrM
## 2.123071e-01 2.157532e-02 -1.089012e-01
## Hhold.fctrMKy Hhold.fctrPKn Income.fctr.Q
## -8.164986e-02 3.776989e-01 -5.982145e-02
## Income.fctr.C Q100689.fctrYes Q101163.fctrDad
## -6.845478e-02 7.776009e-02 -9.435015e-02
## Q101163.fctrMom Q104996.fctrNo Q106042.fctrNo
## 5.478042e-02 -2.122253e-02 -2.683896e-02
## Q106389.fctrNo Q106997.fctrGr Q108855.fctrYes!
## -2.242088e-02 -7.229662e-02 -2.697942e-02
## Q109244.fctrNo Q109244.fctrYes Q110740.fctrMac
## -3.570162e-01 9.252278e-01 2.173880e-02
## Q110740.fctrPC Q112478.fctrNo Q113181.fctrNo
## -7.110575e-02 -3.234141e-02 1.047847e-01
## Q113181.fctrYes Q115195.fctrYes Q115390.fctrNo
## -1.442422e-01 1.409950e-02 -6.846845e-03
## Q115390.fctrYes Q115611.fctrNo Q115611.fctrYes
## 5.491365e-02 1.353109e-01 -3.314197e-01
## Q115899.fctrCs Q116881.fctrHappy Q116881.fctrRight
## 4.819157e-02 1.619212e-02 -1.668260e-01
## Q116953.fctrNo Q118232.fctrId Q118233.fctrNo
## -3.153005e-02 9.756745e-02 -3.955244e-03
## Q119851.fctrNo Q120194.fctrStudy first Q120379.fctrNo
## -1.006952e-01 4.033322e-02 -1.266726e-02
## Q120379.fctrYes Q120472.fctrScience Q120650.fctrYes
## 8.628830e-02 -8.052739e-02 -7.918516e-05
## Q121699.fctrYes Q122120.fctrYes Q122771.fctrPt
## 3.237186e-02 -1.457223e-02 -7.566506e-02
## Q124742.fctrNo Q98197.fctrNo Q98197.fctrYes
## 8.531459e-03 2.842728e-01 -3.409862e-03
## Q98869.fctrNo Q99480.fctrNo Q99480.fctrYes
## 1.875869e-01 3.711351e-02 -4.728446e-02
## YOB.Age.fctr.L YOB.Age.fctr^7 YOB.Age.fctr^8
## 6.134774e-02 -1.275503e-02 -3.263560e-02
## [1] "max lambda < lambdaOpt:"
## (Intercept) Edn.fctr.L Gender.fctrM
## 0.2194026415 0.0250789647 -0.1110166523
## Hhold.fctrMKy Hhold.fctrPKn Income.fctr.Q
## -0.0922968501 0.3888002722 -0.0675789374
## Income.fctr.C Q100689.fctrYes Q101163.fctrDad
## -0.0815213744 0.0873664932 -0.0968737805
## Q101163.fctrMom Q104996.fctrNo Q106042.fctrNo
## 0.0605524619 -0.0294158307 -0.0293613758
## Q106389.fctrNo Q106997.fctrGr Q108855.fctrYes!
## -0.0310950390 -0.0813603310 -0.0347190523
## Q109244.fctrNo Q109244.fctrYes Q110740.fctrMac
## -0.3582630105 0.9302958326 0.0289083519
## Q110740.fctrPC Q111220.fctrYes Q112478.fctrNo
## -0.0732343770 0.0047213847 -0.0404980916
## Q113181.fctrNo Q113181.fctrYes Q113583.fctrTunes
## 0.1096475233 -0.1426961792 0.0001044441
## Q115195.fctrYes Q115390.fctrNo Q115390.fctrYes
## 0.0225819717 -0.0163258587 0.0569504027
## Q115611.fctrNo Q115611.fctrYes Q115899.fctrCs
## 0.1359076104 -0.3370943566 0.0566104909
## Q116881.fctrHappy Q116881.fctrRight Q116953.fctrNo
## 0.0256811888 -0.1671335987 -0.0421907026
## Q118232.fctrId Q118233.fctrNo Q119851.fctrNo
## 0.1082336575 -0.0147693511 -0.1069967848
## Q120194.fctrStudy first Q120379.fctrNo Q120379.fctrYes
## 0.0499363227 -0.0112236709 0.0989672666
## Q120472.fctrScience Q120650.fctrYes Q121699.fctrYes
## -0.0870280043 -0.0114635573 0.0410727129
## Q122120.fctrYes Q122771.fctrPt Q124742.fctrNo
## -0.0240492262 -0.0868530842 0.0215413569
## Q98197.fctrNo Q98869.fctrNo Q99480.fctrNo
## 0.2931645340 0.1970976751 0.0382915209
## Q99480.fctrYes YOB.Age.fctr.L YOB.Age.fctr^7
## -0.0578658541 0.0762294190 -0.0256109530
## YOB.Age.fctr^8
## -0.0451630163
## [1] "myfit_mdl: train diagnostics complete: 27.108000 secs"
## Prediction
## Reference R D
## R 2323 294
## D 1902 1049
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.056034e-01 2.349603e-01 5.926242e-01 6.184720e-01 5.299928e-01
## AccuracyPValue McnemarPValue
## 3.833186e-30 1.013594e-257
## [1] "myfit_mdl: predict complete: 34.714000 secs"
## id
## 1 Final##rcv#glmnet
## feats
## 1 Q109244.fctr,Hhold.fctr,Edn.fctr,Q101163.fctr,Q100689.fctr,Q98078.fctr,Q99716.fctr,Q120379.fctr,Q121699.fctr,Q105840.fctr,Q113583.fctr,Q115195.fctr,Q102089.fctr,Q98059.fctr,Q114386.fctr,Q100680.fctr,Q108342.fctr,Q111848.fctr,YOB.Age.fctr,Q118892.fctr,Q102687.fctr,Q115390.fctr,Q119851.fctr,Q114517.fctr,Q120012.fctr,Q109367.fctr,Q114961.fctr,Q121700.fctr,Q124122.fctr,Q111220.fctr,Q113992.fctr,Q121011.fctr,Q106042.fctr,Q116448.fctr,Q116601.fctr,Q104996.fctr,Q102906.fctr,Q113584.fctr,Q108950.fctr,Q102674.fctr,Q103293.fctr,Q112478.fctr,Q114748.fctr,Q107491.fctr,Q100562.fctr,Q108617.fctr,Q100010.fctr,Q115602.fctr,Q116953.fctr,Q115610.fctr,Q106997.fctr,Q120978.fctr,Q112512.fctr,Q108343.fctr,Q96024.fctr,Q106389.fctr,.rnorm,Q108754.fctr,Q98578.fctr,Q101162.fctr,Q115777.fctr,Q99581.fctr,Q124742.fctr,Q116797.fctr,Q112270.fctr,Q118237.fctr,Q119650.fctr,Q111580.fctr,Q123464.fctr,Q117193.fctr,Q99982.fctr,Q108856.fctr,Q118233.fctr,Q102289.fctr,Q116197.fctr,Income.fctr,Q118232.fctr,Q120194.fctr,Q114152.fctr,Q122770.fctr,Q117186.fctr,Q105655.fctr,Q106993.fctr,Q119334.fctr,Q122120.fctr,Q116441.fctr,Q118117.fctr,Q123621.fctr,Q122769.fctr,Q120650.fctr,Q98869.fctr,Q107869.fctr,Q120014.fctr,Q115899.fctr,Q106388.fctr,Q99480.fctr,Q122771.fctr,Q108855.fctr,Q110740.fctr,Q106272.fctr,Q101596.fctr,Q116881.fctr,Q120472.fctr,Q98197.fctr,Q113181.fctr,Q115611.fctr,Gender.fctr
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 25.56 2.324
## max.AUCpROC.fit max.Sens.fit max.Spec.fit max.AUCROCR.fit
## 1 0.6424822 0.5716469 0.7133175 0.2937147
## opt.prob.threshold.fit max.f.score.fit max.Accuracy.fit
## 1 0.6 0.6790412 0.6343978
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.5926242 0.618472 0.2626432
## max.AccuracySD.fit max.KappaSD.fit
## 1 0.01458328 0.02942434
## [1] "myfit_mdl: exit: 34.730000 secs"rm(ret_lst)
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.data.training", major.inc=FALSE)## label step_major step_minor label_minor bgn end
## 8 fit.data.training 5 0 0 278.319 313.635
## 9 fit.data.training 5 1 1 313.636 NA
## elapsed
## 8 35.316
## 9 NA#stop(here"); glb2Sav()
if (glb_is_classification && glb_is_binomial)
prob_threshold <- glb_models_df[glb_models_df$id == glbMdlSelId,
"opt.prob.threshold.OOB"] else
prob_threshold <- NULL
if (grepl("Ensemble", glbMdlFinId)) {
# Get predictions for each model in ensemble; Outliers that have been moved to OOB might not have been predicted yet
mdlEnsembleComps <- unlist(str_split(subset(glb_models_df,
id == glbMdlFinId)$feats, ","))
if (glb_is_classification && glb_is_binomial)
mdlEnsembleComps <- gsub("\\.prob$", "", mdlEnsembleComps)
mdlEnsembleComps <- gsub(paste0("^",
gsub(".", "\\.", mygetPredictIds(glb_rsp_var)$value, fixed = TRUE)),
"", mdlEnsembleComps)
for (mdl_id in mdlEnsembleComps) {
glbObsTrn <- glb_get_predictions(df = glbObsTrn, mdl_id = mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
glbObsNew <- glb_get_predictions(df = glbObsNew, mdl_id = mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
}
}
glbObsTrn <- glb_get_predictions(df = glbObsTrn, mdl_id = glbMdlFinId,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)## Warning in glb_get_predictions(df = glbObsTrn, mdl_id = glbMdlFinId,
## rsp_var = glb_rsp_var, : Using default probability threshold: 0.95glb_featsimp_df <- myget_feats_importance(mdl=glb_fin_mdl,
featsimp_df=glb_featsimp_df)
#glb_featsimp_df[, paste0(glbMdlFinId, ".imp")] <- glb_featsimp_df$imp
print(glb_featsimp_df)## All.X..rcv.glmnet.imp Final..rcv.glmnet.imp
## Q109244.fctrYes 100.0000000 1.000000e+02
## Hhold.fctrPKn 49.1661885 4.111360e+01
## Q109244.fctrNo 45.5681943 3.856398e+01
## Q115611.fctrYes 28.5463664 3.594481e+01
## Q98197.fctrNo 16.2852705 3.096120e+01
## Q98869.fctrNo 25.9823593 2.054829e+01
## Q116881.fctrRight 16.1046523 1.801125e+01
## Q113181.fctrYes 15.0645836 1.551456e+01
## Q115611.fctrNo 12.5454803 1.461994e+01
## Gender.fctrM 9.7128176 1.181920e+01
## Q113181.fctrNo 11.2439730 1.146362e+01
## Q119851.fctrNo 7.6398025 1.106875e+01
## Q118232.fctrId 10.7065918 1.087203e+01
## Q101163.fctrDad 12.5844125 1.026223e+01
## Q120379.fctrYes 8.0048736 9.719875e+00
## Hhold.fctrMKy 8.3981484 9.153825e+00
## Q120472.fctrScience 7.9096663 8.898966e+00
## Q100689.fctrYes 9.9963048 8.700537e+00
## Q122771.fctrPt 10.0129285 8.525487e+00
## Q106997.fctrGr 4.1885801 8.093498e+00
## Income.fctr.C 7.4087582 7.808056e+00
## Q110740.fctrPC 8.3892982 7.741310e+00
## YOB.Age.fctr.L 11.3449880 7.099717e+00
## Income.fctr.Q 12.7713107 6.705236e+00
## Q101163.fctrMom 6.7542846 6.097245e+00
## Q115390.fctrYes 5.3193973 5.991141e+00
## Q115899.fctrCs 7.6128082 5.471650e+00
## Q99480.fctrYes 5.9665271 5.443518e+00
## Q120194.fctrStudy first 0.4583760 4.661891e+00
## Q99480.fctrNo 12.7202759 4.042722e+00
## YOB.Age.fctr^8 11.9275685 3.925603e+00
## Q121699.fctrYes 6.0868013 3.773720e+00
## Q112478.fctrNo 2.8514946 3.752883e+00
## Q116953.fctrNo 6.9161634 3.746097e+00
## Q108855.fctrYes! 2.4296335 3.160846e+00
## Q106042.fctrNo 6.5953376 2.977412e+00
## Q106389.fctrNo 3.9429465 2.699101e+00
## Q110740.fctrMac 0.1743257 2.576971e+00
## Q104996.fctrNo 3.6848756 2.554284e+00
## Edn.fctr.L 9.0502064 2.441089e+00
## Q116881.fctrHappy 2.0579273 2.053272e+00
## Q122120.fctrYes 7.8979239 1.878088e+00
## Q115195.fctrYes 3.0701510 1.795001e+00
## YOB.Age.fctr^7 7.0570750 1.790989e+00
## Q124742.fctrNo 4.3238031 1.340212e+00
## Q120379.fctrNo 3.1655121 1.320296e+00
## Q115390.fctrNo 0.0000000 1.044548e+00
## Q118233.fctrNo 5.7439564 7.755926e-01
## Q120650.fctrYes 0.0000000 3.757408e-01
## Q98197.fctrYes 11.1024216 2.579574e-01
## Q111220.fctrYes 6.3105242 1.522855e-01
## Q113583.fctrTunes 1.9054136 3.368785e-03
## .rnorm 0.6169315 0.000000e+00
## Edn.fctr.C 0.0000000 0.000000e+00
## Edn.fctr.Q 0.0000000 0.000000e+00
## Edn.fctr^4 0.5022596 0.000000e+00
## Edn.fctr^5 0.0000000 0.000000e+00
## Edn.fctr^6 1.3695208 0.000000e+00
## Edn.fctr^7 1.0851442 0.000000e+00
## Gender.fctrF 1.2934789 0.000000e+00
## Hhold.fctrMKn 0.0000000 0.000000e+00
## Hhold.fctrPKy 0.0000000 0.000000e+00
## Hhold.fctrSKn 0.0000000 0.000000e+00
## Hhold.fctrSKy 10.3937136 0.000000e+00
## Income.fctr.L 0.0000000 0.000000e+00
## Income.fctr^4 0.0000000 0.000000e+00
## Income.fctr^5 0.0000000 0.000000e+00
## Income.fctr^6 0.0000000 0.000000e+00
## Q100010.fctrNo 0.0000000 0.000000e+00
## Q100010.fctrYes 0.0000000 0.000000e+00
## Q100562.fctrNo 0.0000000 0.000000e+00
## Q100562.fctrYes 0.0000000 0.000000e+00
## Q100680.fctrNo 0.0000000 0.000000e+00
## Q100680.fctrYes 0.0000000 0.000000e+00
## Q100689.fctrNo 0.0000000 0.000000e+00
## Q101162.fctrOptimist 0.0000000 0.000000e+00
## Q101162.fctrPessimist 0.1782085 0.000000e+00
## Q101596.fctrNo 0.0000000 0.000000e+00
## Q101596.fctrYes 1.6106039 0.000000e+00
## Q102089.fctrOwn 0.0000000 0.000000e+00
## Q102089.fctrRent 4.3175100 0.000000e+00
## Q102289.fctrNo 0.0000000 0.000000e+00
## Q102289.fctrYes 0.0000000 0.000000e+00
## Q102674.fctrNo 0.0000000 0.000000e+00
## Q102674.fctrYes 0.0000000 0.000000e+00
## Q102687.fctrNo 0.0000000 0.000000e+00
## Q102687.fctrYes 3.1727753 0.000000e+00
## Q102906.fctrNo 0.0000000 0.000000e+00
## Q102906.fctrYes 0.6275475 0.000000e+00
## Q103293.fctrNo 0.0000000 0.000000e+00
## Q103293.fctrYes 0.0000000 0.000000e+00
## Q104996.fctrYes 1.4203649 0.000000e+00
## Q105655.fctrNo 0.0000000 0.000000e+00
## Q105655.fctrYes 1.5936012 0.000000e+00
## Q105840.fctrNo 1.0615732 0.000000e+00
## Q105840.fctrYes 3.6519038 0.000000e+00
## Q106042.fctrYes 0.0000000 0.000000e+00
## Q106272.fctrNo 0.0000000 0.000000e+00
## Q106272.fctrYes 0.0000000 0.000000e+00
## Q106388.fctrNo 0.0000000 0.000000e+00
## Q106388.fctrYes 2.2189974 0.000000e+00
## Q106389.fctrYes 0.0000000 0.000000e+00
## Q106993.fctrNo 0.0000000 0.000000e+00
## Q106993.fctrYes 0.0000000 0.000000e+00
## Q106997.fctrYy 0.0000000 0.000000e+00
## Q107491.fctrNo 0.0000000 0.000000e+00
## Q107491.fctrYes 0.0000000 0.000000e+00
## Q107869.fctrNo 0.9335726 0.000000e+00
## Q107869.fctrYes 0.0000000 0.000000e+00
## Q108342.fctrIn-person 0.0000000 0.000000e+00
## Q108342.fctrOnline 5.5683963 0.000000e+00
## Q108343.fctrNo 0.0000000 0.000000e+00
## Q108343.fctrYes 0.0000000 0.000000e+00
## Q108617.fctrNo 0.0000000 0.000000e+00
## Q108617.fctrYes 0.0000000 0.000000e+00
## Q108754.fctrNo 0.0000000 0.000000e+00
## Q108754.fctrYes 4.3178810 0.000000e+00
## Q108855.fctrUmm... 0.0000000 0.000000e+00
## Q108856.fctrSocialize 3.0189776 0.000000e+00
## Q108856.fctrSpace 0.0000000 0.000000e+00
## Q108950.fctrCautious 0.0000000 0.000000e+00
## Q108950.fctrRisk-friendly 0.0000000 0.000000e+00
## Q109367.fctrNo 0.0000000 0.000000e+00
## Q109367.fctrYes 1.8982707 0.000000e+00
## Q111220.fctrNo 0.6341624 0.000000e+00
## Q111580.fctrDemanding 0.0000000 0.000000e+00
## Q111580.fctrSupportive 0.0000000 0.000000e+00
## Q111848.fctrNo 0.0000000 0.000000e+00
## Q111848.fctrYes 5.1002085 0.000000e+00
## Q112270.fctrNo 0.2657586 0.000000e+00
## Q112270.fctrYes 0.0000000 0.000000e+00
## Q112478.fctrYes 0.0000000 0.000000e+00
## Q112512.fctrNo 0.0000000 0.000000e+00
## Q112512.fctrYes 0.0000000 0.000000e+00
## Q113583.fctrTalk 0.0000000 0.000000e+00
## Q113584.fctrPeople 0.0000000 0.000000e+00
## Q113584.fctrTechnology 0.0000000 0.000000e+00
## Q113992.fctrNo 0.0000000 0.000000e+00
## Q113992.fctrYes 1.0093567 0.000000e+00
## Q114152.fctrNo 0.0000000 0.000000e+00
## Q114152.fctrYes 0.0000000 0.000000e+00
## Q114386.fctrMysterious 0.0000000 0.000000e+00
## Q114386.fctrTMI 0.0000000 0.000000e+00
## Q114517.fctrNo 3.4372729 0.000000e+00
## Q114517.fctrYes 0.0000000 0.000000e+00
## Q114748.fctrNo 0.0000000 0.000000e+00
## Q114748.fctrYes 0.0000000 0.000000e+00
## Q114961.fctrNo 0.0000000 0.000000e+00
## Q114961.fctrYes 0.0000000 0.000000e+00
## Q115195.fctrNo 1.0772420 0.000000e+00
## Q115602.fctrNo 0.0000000 0.000000e+00
## Q115602.fctrYes 0.0000000 0.000000e+00
## Q115610.fctrNo 2.8511607 0.000000e+00
## Q115610.fctrYes 0.0000000 0.000000e+00
## Q115777.fctrEnd 0.0000000 0.000000e+00
## Q115777.fctrStart 0.0000000 0.000000e+00
## Q115899.fctrMe 2.7719360 0.000000e+00
## Q116197.fctrA.M. 2.3083900 0.000000e+00
## Q116197.fctrP.M. 0.0000000 0.000000e+00
## Q116441.fctrNo 0.0000000 0.000000e+00
## Q116441.fctrYes 0.0000000 0.000000e+00
## Q116448.fctrNo 0.0000000 0.000000e+00
## Q116448.fctrYes 0.0000000 0.000000e+00
## Q116601.fctrNo 0.0000000 0.000000e+00
## Q116601.fctrYes 0.0000000 0.000000e+00
## Q116797.fctrNo 0.0000000 0.000000e+00
## Q116797.fctrYes 0.0000000 0.000000e+00
## Q116953.fctrYes 0.0000000 0.000000e+00
## Q117186.fctrCool headed 0.0000000 0.000000e+00
## Q117186.fctrHot headed 0.0000000 0.000000e+00
## Q117193.fctrOdd hours 0.0000000 0.000000e+00
## Q117193.fctrStandard hours 0.0000000 0.000000e+00
## Q118117.fctrNo 0.0000000 0.000000e+00
## Q118117.fctrYes 3.5470296 0.000000e+00
## Q118232.fctrPr 0.0000000 0.000000e+00
## Q118233.fctrYes 0.0000000 0.000000e+00
## Q118237.fctrNo 0.0000000 0.000000e+00
## Q118237.fctrYes 0.0000000 0.000000e+00
## Q118892.fctrNo 1.0010616 0.000000e+00
## Q118892.fctrYes 0.0000000 0.000000e+00
## Q119334.fctrNo 0.0000000 0.000000e+00
## Q119334.fctrYes 0.0000000 0.000000e+00
## Q119650.fctrGiving 0.0000000 0.000000e+00
## Q119650.fctrReceiving 0.0000000 0.000000e+00
## Q119851.fctrYes 8.9965611 0.000000e+00
## Q120012.fctrNo 0.0000000 0.000000e+00
## Q120012.fctrYes 3.1170322 0.000000e+00
## Q120014.fctrNo 1.3795969 0.000000e+00
## Q120014.fctrYes 0.9187812 0.000000e+00
## Q120194.fctrTry first 0.0000000 0.000000e+00
## Q120472.fctrArt 0.0000000 0.000000e+00
## Q120650.fctrNo 1.4727730 0.000000e+00
## Q120978.fctrNo 0.0000000 0.000000e+00
## Q120978.fctrYes 0.0000000 0.000000e+00
## Q121011.fctrNo 0.3860357 0.000000e+00
## Q121011.fctrYes 0.2430506 0.000000e+00
## Q121699.fctrNo 0.0000000 0.000000e+00
## Q121700.fctrNo 0.0000000 0.000000e+00
## Q121700.fctrYes 0.0000000 0.000000e+00
## Q122120.fctrNo 0.0000000 0.000000e+00
## Q122769.fctrNo 0.0000000 0.000000e+00
## Q122769.fctrYes 0.0000000 0.000000e+00
## Q122770.fctrNo 0.0000000 0.000000e+00
## Q122770.fctrYes 0.0000000 0.000000e+00
## Q122771.fctrPc 0.0000000 0.000000e+00
## Q123464.fctrNo 0.0000000 0.000000e+00
## Q123464.fctrYes 0.0000000 0.000000e+00
## Q123621.fctrNo 0.0000000 0.000000e+00
## Q123621.fctrYes 0.4616520 0.000000e+00
## Q124122.fctrNo 1.7842304 0.000000e+00
## Q124122.fctrYes 0.0000000 0.000000e+00
## Q124742.fctrYes 0.0000000 0.000000e+00
## Q96024.fctrNo 0.6364877 0.000000e+00
## Q96024.fctrYes 0.0000000 0.000000e+00
## Q98059.fctrOnly-child 3.9733449 0.000000e+00
## Q98059.fctrYes 4.4995773 0.000000e+00
## Q98078.fctrNo 0.0000000 0.000000e+00
## Q98078.fctrYes 0.0000000 0.000000e+00
## Q98578.fctrNo 0.0000000 0.000000e+00
## Q98578.fctrYes 0.0000000 0.000000e+00
## Q98869.fctrYes 0.0000000 0.000000e+00
## Q99581.fctrNo 0.0000000 0.000000e+00
## Q99581.fctrYes 0.0000000 0.000000e+00
## Q99716.fctrNo 0.0000000 0.000000e+00
## Q99716.fctrYes 5.5086291 0.000000e+00
## Q99982.fctrCheck! 0.0000000 0.000000e+00
## Q99982.fctrNope 0.0000000 0.000000e+00
## YOB.Age.fctr.C 1.3961476 0.000000e+00
## YOB.Age.fctr.Q 0.0000000 0.000000e+00
## YOB.Age.fctr^4 1.3404486 0.000000e+00
## YOB.Age.fctr^5 0.0000000 0.000000e+00
## YOB.Age.fctr^6 0.0000000 0.000000e+00
## imp
## Q109244.fctrYes 1.000000e+02
## Hhold.fctrPKn 4.111360e+01
## Q109244.fctrNo 3.856398e+01
## Q115611.fctrYes 3.594481e+01
## Q98197.fctrNo 3.096120e+01
## Q98869.fctrNo 2.054829e+01
## Q116881.fctrRight 1.801125e+01
## Q113181.fctrYes 1.551456e+01
## Q115611.fctrNo 1.461994e+01
## Gender.fctrM 1.181920e+01
## Q113181.fctrNo 1.146362e+01
## Q119851.fctrNo 1.106875e+01
## Q118232.fctrId 1.087203e+01
## Q101163.fctrDad 1.026223e+01
## Q120379.fctrYes 9.719875e+00
## Hhold.fctrMKy 9.153825e+00
## Q120472.fctrScience 8.898966e+00
## Q100689.fctrYes 8.700537e+00
## Q122771.fctrPt 8.525487e+00
## Q106997.fctrGr 8.093498e+00
## Income.fctr.C 7.808056e+00
## Q110740.fctrPC 7.741310e+00
## YOB.Age.fctr.L 7.099717e+00
## Income.fctr.Q 6.705236e+00
## Q101163.fctrMom 6.097245e+00
## Q115390.fctrYes 5.991141e+00
## Q115899.fctrCs 5.471650e+00
## Q99480.fctrYes 5.443518e+00
## Q120194.fctrStudy first 4.661891e+00
## Q99480.fctrNo 4.042722e+00
## YOB.Age.fctr^8 3.925603e+00
## Q121699.fctrYes 3.773720e+00
## Q112478.fctrNo 3.752883e+00
## Q116953.fctrNo 3.746097e+00
## Q108855.fctrYes! 3.160846e+00
## Q106042.fctrNo 2.977412e+00
## Q106389.fctrNo 2.699101e+00
## Q110740.fctrMac 2.576971e+00
## Q104996.fctrNo 2.554284e+00
## Edn.fctr.L 2.441089e+00
## Q116881.fctrHappy 2.053272e+00
## Q122120.fctrYes 1.878088e+00
## Q115195.fctrYes 1.795001e+00
## YOB.Age.fctr^7 1.790989e+00
## Q124742.fctrNo 1.340212e+00
## Q120379.fctrNo 1.320296e+00
## Q115390.fctrNo 1.044548e+00
## Q118233.fctrNo 7.755926e-01
## Q120650.fctrYes 3.757408e-01
## Q98197.fctrYes 2.579574e-01
## Q111220.fctrYes 1.522855e-01
## Q113583.fctrTunes 3.368785e-03
## .rnorm 0.000000e+00
## Edn.fctr.C 0.000000e+00
## Edn.fctr.Q 0.000000e+00
## Edn.fctr^4 0.000000e+00
## Edn.fctr^5 0.000000e+00
## Edn.fctr^6 0.000000e+00
## Edn.fctr^7 0.000000e+00
## Gender.fctrF 0.000000e+00
## Hhold.fctrMKn 0.000000e+00
## Hhold.fctrPKy 0.000000e+00
## Hhold.fctrSKn 0.000000e+00
## Hhold.fctrSKy 0.000000e+00
## Income.fctr.L 0.000000e+00
## Income.fctr^4 0.000000e+00
## Income.fctr^5 0.000000e+00
## Income.fctr^6 0.000000e+00
## Q100010.fctrNo 0.000000e+00
## Q100010.fctrYes 0.000000e+00
## Q100562.fctrNo 0.000000e+00
## Q100562.fctrYes 0.000000e+00
## Q100680.fctrNo 0.000000e+00
## Q100680.fctrYes 0.000000e+00
## Q100689.fctrNo 0.000000e+00
## Q101162.fctrOptimist 0.000000e+00
## Q101162.fctrPessimist 0.000000e+00
## Q101596.fctrNo 0.000000e+00
## Q101596.fctrYes 0.000000e+00
## Q102089.fctrOwn 0.000000e+00
## Q102089.fctrRent 0.000000e+00
## Q102289.fctrNo 0.000000e+00
## Q102289.fctrYes 0.000000e+00
## Q102674.fctrNo 0.000000e+00
## Q102674.fctrYes 0.000000e+00
## Q102687.fctrNo 0.000000e+00
## Q102687.fctrYes 0.000000e+00
## Q102906.fctrNo 0.000000e+00
## Q102906.fctrYes 0.000000e+00
## Q103293.fctrNo 0.000000e+00
## Q103293.fctrYes 0.000000e+00
## Q104996.fctrYes 0.000000e+00
## Q105655.fctrNo 0.000000e+00
## Q105655.fctrYes 0.000000e+00
## Q105840.fctrNo 0.000000e+00
## Q105840.fctrYes 0.000000e+00
## Q106042.fctrYes 0.000000e+00
## Q106272.fctrNo 0.000000e+00
## Q106272.fctrYes 0.000000e+00
## Q106388.fctrNo 0.000000e+00
## Q106388.fctrYes 0.000000e+00
## Q106389.fctrYes 0.000000e+00
## Q106993.fctrNo 0.000000e+00
## Q106993.fctrYes 0.000000e+00
## Q106997.fctrYy 0.000000e+00
## Q107491.fctrNo 0.000000e+00
## Q107491.fctrYes 0.000000e+00
## Q107869.fctrNo 0.000000e+00
## Q107869.fctrYes 0.000000e+00
## Q108342.fctrIn-person 0.000000e+00
## Q108342.fctrOnline 0.000000e+00
## Q108343.fctrNo 0.000000e+00
## Q108343.fctrYes 0.000000e+00
## Q108617.fctrNo 0.000000e+00
## Q108617.fctrYes 0.000000e+00
## Q108754.fctrNo 0.000000e+00
## Q108754.fctrYes 0.000000e+00
## Q108855.fctrUmm... 0.000000e+00
## Q108856.fctrSocialize 0.000000e+00
## Q108856.fctrSpace 0.000000e+00
## Q108950.fctrCautious 0.000000e+00
## Q108950.fctrRisk-friendly 0.000000e+00
## Q109367.fctrNo 0.000000e+00
## Q109367.fctrYes 0.000000e+00
## Q111220.fctrNo 0.000000e+00
## Q111580.fctrDemanding 0.000000e+00
## Q111580.fctrSupportive 0.000000e+00
## Q111848.fctrNo 0.000000e+00
## Q111848.fctrYes 0.000000e+00
## Q112270.fctrNo 0.000000e+00
## Q112270.fctrYes 0.000000e+00
## Q112478.fctrYes 0.000000e+00
## Q112512.fctrNo 0.000000e+00
## Q112512.fctrYes 0.000000e+00
## Q113583.fctrTalk 0.000000e+00
## Q113584.fctrPeople 0.000000e+00
## Q113584.fctrTechnology 0.000000e+00
## Q113992.fctrNo 0.000000e+00
## Q113992.fctrYes 0.000000e+00
## Q114152.fctrNo 0.000000e+00
## Q114152.fctrYes 0.000000e+00
## Q114386.fctrMysterious 0.000000e+00
## Q114386.fctrTMI 0.000000e+00
## Q114517.fctrNo 0.000000e+00
## Q114517.fctrYes 0.000000e+00
## Q114748.fctrNo 0.000000e+00
## Q114748.fctrYes 0.000000e+00
## Q114961.fctrNo 0.000000e+00
## Q114961.fctrYes 0.000000e+00
## Q115195.fctrNo 0.000000e+00
## Q115602.fctrNo 0.000000e+00
## Q115602.fctrYes 0.000000e+00
## Q115610.fctrNo 0.000000e+00
## Q115610.fctrYes 0.000000e+00
## Q115777.fctrEnd 0.000000e+00
## Q115777.fctrStart 0.000000e+00
## Q115899.fctrMe 0.000000e+00
## Q116197.fctrA.M. 0.000000e+00
## Q116197.fctrP.M. 0.000000e+00
## Q116441.fctrNo 0.000000e+00
## Q116441.fctrYes 0.000000e+00
## Q116448.fctrNo 0.000000e+00
## Q116448.fctrYes 0.000000e+00
## Q116601.fctrNo 0.000000e+00
## Q116601.fctrYes 0.000000e+00
## Q116797.fctrNo 0.000000e+00
## Q116797.fctrYes 0.000000e+00
## Q116953.fctrYes 0.000000e+00
## Q117186.fctrCool headed 0.000000e+00
## Q117186.fctrHot headed 0.000000e+00
## Q117193.fctrOdd hours 0.000000e+00
## Q117193.fctrStandard hours 0.000000e+00
## Q118117.fctrNo 0.000000e+00
## Q118117.fctrYes 0.000000e+00
## Q118232.fctrPr 0.000000e+00
## Q118233.fctrYes 0.000000e+00
## Q118237.fctrNo 0.000000e+00
## Q118237.fctrYes 0.000000e+00
## Q118892.fctrNo 0.000000e+00
## Q118892.fctrYes 0.000000e+00
## Q119334.fctrNo 0.000000e+00
## Q119334.fctrYes 0.000000e+00
## Q119650.fctrGiving 0.000000e+00
## Q119650.fctrReceiving 0.000000e+00
## Q119851.fctrYes 0.000000e+00
## Q120012.fctrNo 0.000000e+00
## Q120012.fctrYes 0.000000e+00
## Q120014.fctrNo 0.000000e+00
## Q120014.fctrYes 0.000000e+00
## Q120194.fctrTry first 0.000000e+00
## Q120472.fctrArt 0.000000e+00
## Q120650.fctrNo 0.000000e+00
## Q120978.fctrNo 0.000000e+00
## Q120978.fctrYes 0.000000e+00
## Q121011.fctrNo 0.000000e+00
## Q121011.fctrYes 0.000000e+00
## Q121699.fctrNo 0.000000e+00
## Q121700.fctrNo 0.000000e+00
## Q121700.fctrYes 0.000000e+00
## Q122120.fctrNo 0.000000e+00
## Q122769.fctrNo 0.000000e+00
## Q122769.fctrYes 0.000000e+00
## Q122770.fctrNo 0.000000e+00
## Q122770.fctrYes 0.000000e+00
## Q122771.fctrPc 0.000000e+00
## Q123464.fctrNo 0.000000e+00
## Q123464.fctrYes 0.000000e+00
## Q123621.fctrNo 0.000000e+00
## Q123621.fctrYes 0.000000e+00
## Q124122.fctrNo 0.000000e+00
## Q124122.fctrYes 0.000000e+00
## Q124742.fctrYes 0.000000e+00
## Q96024.fctrNo 0.000000e+00
## Q96024.fctrYes 0.000000e+00
## Q98059.fctrOnly-child 0.000000e+00
## Q98059.fctrYes 0.000000e+00
## Q98078.fctrNo 0.000000e+00
## Q98078.fctrYes 0.000000e+00
## Q98578.fctrNo 0.000000e+00
## Q98578.fctrYes 0.000000e+00
## Q98869.fctrYes 0.000000e+00
## Q99581.fctrNo 0.000000e+00
## Q99581.fctrYes 0.000000e+00
## Q99716.fctrNo 0.000000e+00
## Q99716.fctrYes 0.000000e+00
## Q99982.fctrCheck! 0.000000e+00
## Q99982.fctrNope 0.000000e+00
## YOB.Age.fctr.C 0.000000e+00
## YOB.Age.fctr.Q 0.000000e+00
## YOB.Age.fctr^4 0.000000e+00
## YOB.Age.fctr^5 0.000000e+00
## YOB.Age.fctr^6 0.000000e+00if (glb_is_classification && glb_is_binomial)
glb_analytics_diag_plots(obs_df=glbObsTrn, mdl_id=glbMdlFinId,
prob_threshold=glb_models_df[glb_models_df$id == glbMdlSelId,
"opt.prob.threshold.OOB"]) else
glb_analytics_diag_plots(obs_df=glbObsTrn, mdl_id=glbMdlFinId) ## Warning in glb_analytics_diag_plots(obs_df = glbObsTrn, mdl_id =
## glbMdlFinId, : Limiting important feature scatter plots to 5 out of 107
## [1] "Min/Max Boundaries: "
## [1] "Inaccurate: "
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 1 1309 D NA
## 2 2641 D NA
## 3 1311 D 0.1980716
## 4 1393 D NA
## 5 3006 D 0.1889793
## 6 4956 D 0.2342246
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 1 <NA> NA
## 2 <NA> NA
## 3 R TRUE
## 4 <NA> NA
## 5 R TRUE
## 6 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs Party.fctr.All.X..rcv.glmnet.is.acc
## 1 NA NA
## 2 NA NA
## 3 0.8019284 FALSE
## 4 NA NA
## 5 0.8110207 FALSE
## 6 0.7657754 FALSE
## Party.fctr.Final..rcv.glmnet.prob Party.fctr.Final..rcv.glmnet
## 1 0.2061977 R
## 2 0.2256276 R
## 3 0.2257340 R
## 4 0.2264941 R
## 5 0.2283662 R
## 6 0.2306508 R
## Party.fctr.Final..rcv.glmnet.err Party.fctr.Final..rcv.glmnet.err.abs
## 1 TRUE 0.7938023
## 2 TRUE 0.7743724
## 3 TRUE 0.7742660
## 4 TRUE 0.7735059
## 5 TRUE 0.7716338
## 6 TRUE 0.7693492
## Party.fctr.Final..rcv.glmnet.is.acc
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## Party.fctr.Final..rcv.glmnet.accurate Party.fctr.Final..rcv.glmnet.error
## 1 FALSE -0.7438023
## 2 FALSE -0.7243724
## 3 FALSE -0.7242660
## 4 FALSE -0.7235059
## 5 FALSE -0.7216338
## 6 FALSE -0.7193492
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 981 2032 D 0.5907323
## 1286 1927 D 0.5154229
## 1752 6471 D 0.6233997
## 2085 3775 D 0.6324316
## 2417 2246 D 0.8057095
## 2786 5411 D 0.8373183
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 981 R TRUE
## 1286 R TRUE
## 1752 R TRUE
## 2085 R TRUE
## 2417 R TRUE
## 2786 R TRUE
## Party.fctr.All.X..rcv.glmnet.err.abs
## 981 0.4092677
## 1286 0.4845771
## 1752 0.3766003
## 2085 0.3675684
## 2417 0.1942905
## 2786 0.1626817
## Party.fctr.All.X..rcv.glmnet.is.acc Party.fctr.Final..rcv.glmnet.prob
## 981 FALSE 0.5130441
## 1286 FALSE 0.5364791
## 1752 FALSE 0.5792499
## 2085 FALSE 0.6354445
## 2417 FALSE 0.7564907
## 2786 FALSE 0.8379298
## Party.fctr.Final..rcv.glmnet Party.fctr.Final..rcv.glmnet.err
## 981 R TRUE
## 1286 R TRUE
## 1752 R TRUE
## 2085 R TRUE
## 2417 R TRUE
## 2786 R TRUE
## Party.fctr.Final..rcv.glmnet.err.abs
## 981 0.4869559
## 1286 0.4635209
## 1752 0.4207501
## 2085 0.3645555
## 2417 0.2435093
## 2786 0.1620702
## Party.fctr.Final..rcv.glmnet.is.acc
## 981 FALSE
## 1286 FALSE
## 1752 FALSE
## 2085 FALSE
## 2417 FALSE
## 2786 FALSE
## Party.fctr.Final..rcv.glmnet.accurate
## 981 FALSE
## 1286 FALSE
## 1752 FALSE
## 2085 FALSE
## 2417 FALSE
## 2786 FALSE
## Party.fctr.Final..rcv.glmnet.error
## 981 -0.4369559
## 1286 -0.4135209
## 1752 -0.3707501
## 2085 -0.3145555
## 2417 -0.1935093
## 2786 -0.1120702
## USER_ID Party.fctr Party.fctr.All.X..rcv.glmnet.prob
## 2946 431 D 0.9286657
## 2947 1964 D 0.9189075
## 2948 4143 D 0.9187767
## 2949 3425 D 0.9382848
## 2950 1035 D 0.9434543
## 2951 5082 D NA
## Party.fctr.All.X..rcv.glmnet Party.fctr.All.X..rcv.glmnet.err
## 2946 R TRUE
## 2947 R TRUE
## 2948 R TRUE
## 2949 R TRUE
## 2950 R TRUE
## 2951 <NA> NA
## Party.fctr.All.X..rcv.glmnet.err.abs
## 2946 0.07133426
## 2947 0.08109251
## 2948 0.08122335
## 2949 0.06171523
## 2950 0.05654570
## 2951 NA
## Party.fctr.All.X..rcv.glmnet.is.acc Party.fctr.Final..rcv.glmnet.prob
## 2946 FALSE 0.8932396
## 2947 FALSE 0.8950357
## 2948 FALSE 0.8961494
## 2949 FALSE 0.9096633
## 2950 FALSE 0.9101212
## 2951 NA 0.9105865
## Party.fctr.Final..rcv.glmnet Party.fctr.Final..rcv.glmnet.err
## 2946 R TRUE
## 2947 R TRUE
## 2948 R TRUE
## 2949 R TRUE
## 2950 R TRUE
## 2951 R TRUE
## Party.fctr.Final..rcv.glmnet.err.abs
## 2946 0.10676036
## 2947 0.10496427
## 2948 0.10385059
## 2949 0.09033672
## 2950 0.08987885
## 2951 0.08941350
## Party.fctr.Final..rcv.glmnet.is.acc
## 2946 FALSE
## 2947 FALSE
## 2948 FALSE
## 2949 FALSE
## 2950 FALSE
## 2951 FALSE
## Party.fctr.Final..rcv.glmnet.accurate
## 2946 FALSE
## 2947 FALSE
## 2948 FALSE
## 2949 FALSE
## 2950 FALSE
## 2951 FALSE
## Party.fctr.Final..rcv.glmnet.error
## 2946 -0.05676036
## 2947 -0.05496427
## 2948 -0.05385059
## 2949 -0.04033672
## 2950 -0.03987885
## 2951 -0.03941350
dsp_feats_vctr <- c(NULL)
for(var in grep(".imp", names(glb_feats_df), fixed=TRUE, value=TRUE))
dsp_feats_vctr <- union(dsp_feats_vctr,
glb_feats_df[!is.na(glb_feats_df[, var]), "id"])
# print(glbObsTrn[glbObsTrn$UniqueID %in% FN_OOB_ids,
# grep(glb_rsp_var, names(glbObsTrn), value=TRUE)])
print(setdiff(names(glbObsTrn), names(glbObsAll)))## [1] "Party.fctr.Final..rcv.glmnet.prob"
## [2] "Party.fctr.Final..rcv.glmnet"
## [3] "Party.fctr.Final..rcv.glmnet.err"
## [4] "Party.fctr.Final..rcv.glmnet.err.abs"
## [5] "Party.fctr.Final..rcv.glmnet.is.acc"for (col in setdiff(names(glbObsTrn), names(glbObsAll)))
# Merge or cbind ?
glbObsAll[glbObsAll$.src == "Train", col] <- glbObsTrn[, col]
print(setdiff(names(glbObsFit), names(glbObsAll)))## character(0)print(setdiff(names(glbObsOOB), names(glbObsAll)))## character(0)for (col in setdiff(names(glbObsOOB), names(glbObsAll)))
# Merge or cbind ?
glbObsAll[glbObsAll$.lcn == "OOB", col] <- glbObsOOB[, col]
print(setdiff(names(glbObsNew), names(glbObsAll)))## character(0)#glb2Sav(); all.equal(savObsAll, glbObsAll); all.equal(sav_models_lst, glb_models_lst)
#load(file = paste0(glbOut$pfx, "dsk_knitr.RData"))
#cmpCols <- names(glbObsAll)[!grepl("\\.Final\\.", names(glbObsAll))]; all.equal(savObsAll[, cmpCols], glbObsAll[, cmpCols]); all.equal(savObsAll[, "H.P.http"], glbObsAll[, "H.P.http"]);
replay.petrisim(pn = glb_analytics_pn,
replay.trans = (glb_analytics_avl_objs <- c(glb_analytics_avl_objs,
"data.training.all.prediction","model.final")), flip_coord = TRUE)## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: model.selected
## 1.0000 3 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.training.all.prediction
## 2.0000 5 2 0 0 1## Warning in replay.petrisim(pn = glb_analytics_pn, replay.trans =
## (glb_analytics_avl_objs <- c(glb_analytics_avl_objs, : Transition:
## model.final not enabled; adding missing token(s)## Warning in replay.petrisim(pn = glb_analytics_pn, replay.trans
## = (glb_analytics_avl_objs <- c(glb_analytics_avl_objs, : Place:
## fit.data.training.all: added 1 missing token## 2.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: model.final
## 3.0000 4 2 0 1 1
glb_chunks_df <- myadd_chunk(glb_chunks_df, "predict.data.new", major.inc = TRUE)## label step_major step_minor label_minor bgn end
## 9 fit.data.training 5 1 1 313.636 323.041
## 10 predict.data.new 6 0 0 323.042 NA
## elapsed
## 9 9.405
## 10 NAStep 6.0: predict data new
## Warning in glb_get_predictions(obs_df, mdl_id = glbMdlFinId, rsp_var =
## glb_rsp_var, : Using default probability threshold: 0.95
## Warning in glb_get_predictions(obs_df, mdl_id = glbMdlFinId, rsp_var =
## glb_rsp_var, : Using default probability threshold: 0.95## Warning in glb_analytics_diag_plots(obs_df = glbObsNew, mdl_id =
## glbMdlFinId, : Limiting important feature scatter plots to 5 out of 107## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## Warning: Removed 1392 rows containing missing values (geom_point).
## NULL## Loading required package: tidyr##
## Attaching package: 'tidyr'## The following object is masked from 'package:Matrix':
##
## expand## [1] "OOBobs total range outliers: 0"
## [1] "newobs total range outliers: 0"## [1] 0.95## [1] "glbMdlSelId: All.X##rcv#glmnet"## [1] "glbMdlFinId: Final##rcv#glmnet"## [1] "Cross Validation issues:"
## MFO###myMFO_classfr Random###myrandom_classfr
## 0 0
## Max.cor.Y.rcv.1X1###glmnet
## 0## max.Accuracy.OOB max.AUCROCR.OOB
## All.X##rcv#glm 0.4825112 0.4526227
## Random###myrandom_classfr 0.4699552 0.5178149
## MFO###myMFO_classfr 0.4699552 0.5000000
## Max.cor.Y##rcv#rpart 0.4699552 0.4999354
## Max.cor.Y.rcv.1X1###glmnet 0.4699552 0.4910312
## Interact.High.cor.Y##rcv#glmnet 0.4699552 0.4731743
## Low.cor.X##rcv#glmnet 0.4699552 0.4400873
## All.X##rcv#glmnet 0.4699552 0.4400873
## Final##rcv#glmnet NA NA
## max.AUCpROC.OOB max.Accuracy.fit
## All.X##rcv#glm 0.5336537 0.6290918
## Random###myrandom_classfr 0.5268661 0.4700202
## MFO###myMFO_classfr 0.5000000 0.4700202
## Max.cor.Y##rcv#rpart 0.4999322 0.6227314
## Max.cor.Y.rcv.1X1###glmnet 0.4999322 0.5930833
## Interact.High.cor.Y##rcv#glmnet 0.5157790 0.6276719
## Low.cor.X##rcv#glmnet 0.5490597 0.6543940
## All.X##rcv#glmnet 0.5490597 0.6543940
## Final##rcv#glmnet NA 0.6343978
## opt.prob.threshold.fit
## All.X##rcv#glm 0.65
## Random###myrandom_classfr 0.55
## MFO###myMFO_classfr 0.50
## Max.cor.Y##rcv#rpart 0.55
## Max.cor.Y.rcv.1X1###glmnet 0.60
## Interact.High.cor.Y##rcv#glmnet 0.65
## Low.cor.X##rcv#glmnet 0.60
## All.X##rcv#glmnet 0.60
## Final##rcv#glmnet 0.60
## opt.prob.threshold.OOB
## All.X##rcv#glm 0.95
## Random###myrandom_classfr 0.55
## MFO###myMFO_classfr 0.50
## Max.cor.Y##rcv#rpart 0.90
## Max.cor.Y.rcv.1X1###glmnet 0.90
## Interact.High.cor.Y##rcv#glmnet 1.00
## Low.cor.X##rcv#glmnet 0.95
## All.X##rcv#glmnet 0.95
## Final##rcv#glmnet NA## [1] "All.X##rcv#glmnet OOB confusion matrix & accuracy: "
## Prediction
## Reference R D
## R 524 0
## D 591 0## err.abs.fit.sum err.abs.OOB.sum err.abs.trn.sum err.abs.new.sum
## No 881.0781 243.08985 1137.2111 NA
## NA 829.2116 211.31349 1048.3454 NA
## Yes 199.1027 83.86404 297.7102 NA
## .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst .n.Fit .n.New.R .n.OOB
## No 0.4403773 0.4466368 0.4468391 1961 622 498
## NA 0.3920952 0.3928251 0.3929598 1746 547 438
## Yes 0.1675275 0.1605381 0.1602011 746 223 179
## .n.Trn.D .n.Trn.R .n.Tst .n.fit .n.new .n.trn err.abs.OOB.mean
## No 1038 1421 622 1961 622 2459 0.4881322
## NA 1171 1013 547 1746 547 2184 0.4824509
## Yes 742 183 223 746 223 925 0.4685142
## err.abs.fit.mean err.abs.new.mean err.abs.trn.mean
## No 0.4493004 NA 0.4624689
## NA 0.4749207 NA 0.4800116
## Yes 0.2668937 NA 0.3218489
## err.abs.fit.sum err.abs.OOB.sum err.abs.trn.sum err.abs.new.sum
## 1909.392454 538.267380 2483.266662 NA
## .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst .n.Fit
## 1.000000 1.000000 1.000000 4453.000000
## .n.New.R .n.OOB .n.Trn.D .n.Trn.R
## 1392.000000 1115.000000 2951.000000 2617.000000
## .n.Tst .n.fit .n.new .n.trn
## 1392.000000 4453.000000 1392.000000 5568.000000
## err.abs.OOB.mean err.abs.fit.mean err.abs.new.mean err.abs.trn.mean
## 1.439097 1.191115 NA 1.264329## [1] "Features Importance for selected models:"## All.X..rcv.glmnet.imp Final..rcv.glmnet.imp
## Q109244.fctrYes 100.000000 100.0000000
## Hhold.fctrPKn 49.166189 41.1135979
## Q109244.fctrNo 45.568194 38.5639836
## Q115611.fctrYes 28.546366 35.9448112
## Q98869.fctrNo 25.982359 20.5482906
## Q98197.fctrNo 16.285270 30.9612021
## Q116881.fctrRight 16.104652 18.0112480
## Q113181.fctrYes 15.064584 15.5145602
## Income.fctr.Q 12.771311 6.7052356
## Q99480.fctrNo 12.720276 4.0427224
## Q101163.fctrDad 12.584413 10.2622333
## Q115611.fctrNo 12.545480 14.6199445
## YOB.Age.fctr^8 11.927568 3.9256031
## YOB.Age.fctr.L 11.344988 7.0997165
## Q113181.fctrNo 11.243973 11.4636192
## Q98197.fctrYes 11.102422 0.2579574
## Q118232.fctrId 10.706592 10.8720293
## Hhold.fctrSKy 10.393714 0.0000000
## Q122771.fctrPt 10.012929 8.5254872
## Gender.fctrM 9.712818 11.8191970
## Q119851.fctrNo 7.639803 11.0687511## [1] "glbObsNew prediction stats:"##
## R D
## 1392 0## label step_major step_minor label_minor bgn end
## 10 predict.data.new 6 0 0 323.042 339.049
## 11 display.session.info 7 0 0 339.049 NA
## elapsed
## 10 16.007
## 11 NANull Hypothesis (\(\sf{H_{0}}\)): mpg is not impacted by am_fctr.
The variance by am_fctr appears to be independent. #{r q1, cache=FALSE} # print(t.test(subset(cars_df, am_fctr == "automatic")$mpg, # subset(cars_df, am_fctr == "manual")$mpg, # var.equal=FALSE)$conf) # We reject the null hypothesis i.e. we have evidence to conclude that am_fctr impacts mpg (95% confidence). Manual transmission is better for miles per gallon versus automatic transmission.
## label step_major step_minor label_minor bgn
## 2 partition.data.training 2 0 0 10.297
## 4 fit.models 4 0 0 121.782
## 5 fit.models 4 1 1 192.390
## 8 fit.data.training 5 0 0 278.319
## 10 predict.data.new 6 0 0 323.042
## 6 fit.models 4 2 2 260.521
## 9 fit.data.training 5 1 1 313.636
## 3 select.features 3 0 0 115.764
## 7 fit.models 4 3 3 273.672
## 1 cluster.data 1 0 0 9.076
## end elapsed duration
## 2 115.763 105.467 105.466
## 4 192.389 70.607 70.607
## 5 260.520 68.131 68.130
## 8 313.635 35.316 35.316
## 10 339.049 16.007 16.007
## 6 273.671 13.150 13.150
## 9 323.041 9.405 9.405
## 3 121.782 6.018 6.018
## 7 278.319 4.647 4.647
## 1 10.296 1.220 1.220
## [1] "Total Elapsed Time: 339.049 secs"